{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1408,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":1408,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"3f881fb6d4c4","filters":{"topic":"Speech and Audio Processing"}},"results":[{"id":"W2112739286","doi":"10.1109/icassp.2013.6639347","title":"Deep convolutional neural networks for LVCSR","year":2013,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1070,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Convolutional neural network; Pooling; Artificial intelligence; Speech recognition; Focus (optics); Vocabulary; Feature (linguistics); Deep neural networks; Artificial neural network; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.01317611183544196,"gpt":0.2283655173825606,"spread":0.2151894055471187,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005204092,0.00005658353,0.00005615846,0.00002054172,0.000103354,0.0001846417,0.0003165749,0.00002779826,0.0001033571],"category_scores_gemma":[0.00001485273,0.00004512572,0.00003502063,0.00009746033,0.00001910615,0.0005095224,0.00006597864,0.00004067319,0.00005438174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009614729,"about_ca_system_score_gemma":0.000016041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009164163,"about_ca_topic_score_gemma":0.000003353092,"domain_scores_codex":[0.9994488,0.000005889142,0.00008636623,0.0001602606,0.00007839449,0.0002202783],"domain_scores_gemma":[0.9996454,0.00005621303,0.00002553608,0.0001259407,0.00008377796,0.0000631614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004748307,0.00006135086,0.002967115,0.00001680102,0.00001998803,0.000002269526,0.000099711,0.01211643,0.001372491,0.05180006,0.05881143,0.8727276],"study_design_scores_gemma":[0.0001510827,0.00002140573,0.00167901,0.000001659762,8.015528e-7,0.000006852016,0.000005038109,0.9886472,0.001419038,0.007076199,0.0009166571,0.00007507652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002868437,0.0001545545,0.9924494,0.001865729,0.0002680612,0.0001144176,8.536671e-8,0.0001247883,0.002154539],"genre_scores_gemma":[0.7286384,0.000001190555,0.2678938,0.002369784,0.000187634,0.00003926325,0.000001844267,0.000003814485,0.0008642584],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9765307,"threshold_uncertainty_score":0.1840173,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061074721","doi":"10.1007/978-3-540-78612-2","title":"Microphone Array Signal Processing","year":2008,"lang":"en","type":"book","venue":"Springer topics in signal processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":901,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Signal processing; Microphone array; Computer science; SIGNAL (programming language); Array processing; Acoustics; Speech recognition; Microphone; Digital signal processing; Physics; Telecommunications; Computer hardware","retraction":null,"screen_n_in":null,"score":{"opus":0.02083511194856587,"gpt":0.243817188674715,"spread":0.2229820767261491,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005870875,0.001008304,0.001097805,0.0008275962,0.0006750044,0.001126928,0.002513554,0.0008203546,0.00006422153],"category_scores_gemma":[0.00002668046,0.001048662,0.0002665729,0.0008974688,0.0003278309,0.001497337,0.0005591011,0.002117685,0.0001134614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007496076,"about_ca_system_score_gemma":0.003611243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001073129,"about_ca_topic_score_gemma":0.00001337043,"domain_scores_codex":[0.9943322,0.00007862974,0.001256794,0.001824792,0.001169161,0.001338451],"domain_scores_gemma":[0.9976202,0.0000788951,0.0009107376,0.0006943304,0.0003982096,0.0002976441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002567479,0.0001729977,0.0002806531,0.001596274,0.00003329846,0.0007578497,0.002126981,0.0001466546,0.0158631,0.0002026475,0.001890753,0.9769031],"study_design_scores_gemma":[0.003377312,0.0004180771,0.0003809641,0.01825474,0.0001433729,0.001189292,0.0001356243,0.008052459,0.3687566,0.05737863,0.5340702,0.007842736],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003502415,0.02463434,0.7072541,0.0006307329,0.0005095762,0.000561019,0.000005348765,0.0007311304,0.2653235],"genre_scores_gemma":[0.033378,0.0006705829,0.5274393,0.002245351,0.006132293,0.0001150374,0.00004829749,0.0004459713,0.4295252],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9690604,"threshold_uncertainty_score":0.99991,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2113131123","doi":"10.1109/tsa.2005.860851","title":"New insights into the noise reduction Wiener filter","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":694,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Wiener filter; Noise reduction; Intelligibility (philosophy); Wiener deconvolution; Filter (signal processing); Noise (video); Speech recognition; Distortion (music); Reduction (mathematics); Computer science; Noise measurement; Mathematics; Speech enhancement; Salt-and-pepper noise; Algorithm; Median filter; Artificial intelligence; Telecommunications; Bandwidth (computing); Computer vision; Amplifier","retraction":null,"screen_n_in":null,"score":{"opus":0.007253780499054257,"gpt":0.2282763972815397,"spread":0.2210226167824855,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001657081,0.0002381092,0.0001693314,0.0001892041,0.0007634055,0.0005778387,0.0003868194,0.00009583023,0.00003789326],"category_scores_gemma":[0.000005143468,0.0001674614,0.00007262505,0.0006651237,0.00008347175,0.001018905,0.00000605983,0.0003200464,0.00003127495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005238469,"about_ca_system_score_gemma":0.0001424202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000355727,"about_ca_topic_score_gemma":0.0001824135,"domain_scores_codex":[0.9985626,0.00005160524,0.0002537222,0.0004952078,0.0003063999,0.0003304076],"domain_scores_gemma":[0.9993022,0.0000380673,0.000112974,0.0003593782,0.00006711386,0.0001202379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001401589,0.00004818799,0.000004257439,0.00002862643,0.000008541268,0.00002061414,0.004213602,0.0004068674,0.07085279,0.00002221004,0.0004035392,0.9239768],"study_design_scores_gemma":[0.0005037616,0.00006125556,0.00009158882,0.000129763,0.00003011671,0.0001770942,0.0005153624,0.004772837,0.9899597,0.001650658,0.001763024,0.0003448502],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06864345,0.003743509,0.924084,0.001479609,0.0003439104,0.0001365495,5.665891e-7,0.0002860485,0.001282347],"genre_scores_gemma":[0.9183864,0.00005285643,0.07770721,0.0004332244,0.0003362878,0.00001524237,0.000001432622,0.00002125681,0.003046067],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9236319,"threshold_uncertainty_score":0.6828877,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3163652268","doi":"10.1109/icassp39728.2021.9413901","title":"Attention Is All You Need In Speech Separation","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":613,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Recurrent neural network; Transformer; Computation; Artificial intelligence; Upsampling; Speech recognition; Artificial neural network; Algorithm; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02245504284799524,"gpt":0.2955110363863656,"spread":0.2730559935383703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001049901,0.00005015689,0.00005922691,0.0000501787,0.00002752568,0.0001729363,0.0001487932,0.00003165988,0.00008353693],"category_scores_gemma":[0.00001367691,0.00004817088,0.00002469323,0.0003773923,0.000004796862,0.0004948738,0.00006776701,0.00005094688,0.0001391309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002269914,"about_ca_system_score_gemma":0.00005013559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002015335,"about_ca_topic_score_gemma":0.00007020854,"domain_scores_codex":[0.9993881,0.00001839054,0.0001149026,0.0002109673,0.0001354275,0.0001321916],"domain_scores_gemma":[0.9997068,0.00000830305,0.00002599815,0.0001759764,0.00005375284,0.00002918165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004401712,0.0001700914,0.02076518,0.00003380898,0.00001453818,0.0001884817,0.001126351,0.00004324059,0.3966171,0.003076237,0.01342779,0.5645328],"study_design_scores_gemma":[0.0003219254,0.00001503229,0.01293226,0.00001912384,0.00000197826,0.00003628099,0.0001064504,0.01311285,0.9640191,0.00391944,0.005380275,0.00013528],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.592998,0.0001468211,0.3774227,0.008893668,0.0002581216,0.00005467564,2.577196e-7,0.0001249913,0.02010078],"genre_scores_gemma":[0.7714858,0.00002222578,0.2159045,0.004210659,0.00006907846,0.000003545482,0.000006208896,0.000004930225,0.008293042],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5674021,"threshold_uncertainty_score":0.1964352,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104422351","doi":"10.1109/iros.2003.1248813","title":"Robust sound source localization using a microphone array on a mobile robot","year":2004,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":387,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Microphone array; Computer science; Mobile robot; Robot; Acoustic source localization; Sound localization; Omnidirectional antenna; Computer vision; Microphone; Acoustics; Sound (geography); Artificial intelligence; Antenna (radio); Sound pressure","retraction":null,"screen_n_in":null,"score":{"opus":0.04378815510899821,"gpt":0.2633118744958775,"spread":0.2195237193868793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002067926,0.0003838979,0.0003536923,0.0002367704,0.0002647746,0.0009182214,0.001048022,0.0002995678,0.000043293],"category_scores_gemma":[0.00002510745,0.0003590961,0.0001465988,0.0004343809,0.00006238183,0.000232993,0.0006840166,0.000492954,0.00009215991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003615217,"about_ca_system_score_gemma":0.0004832537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001992407,"about_ca_topic_score_gemma":0.00003298953,"domain_scores_codex":[0.9977062,0.00004930047,0.0003834917,0.00100612,0.0004159015,0.0004389546],"domain_scores_gemma":[0.9985042,0.00003026552,0.0002962048,0.0008905368,0.0001452638,0.0001335369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004570947,0.00009363706,0.00004769613,0.0001037214,0.00001812526,0.00001045105,0.0006137087,0.9741518,0.02063603,0.00002770091,0.00005110157,0.00424146],"study_design_scores_gemma":[0.0006934173,0.0001312476,0.00002064988,0.001182985,0.00003407136,0.00008831308,0.0001463784,0.1950186,0.7858772,0.0149071,0.0006888962,0.001211125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01375004,0.0003953048,0.9832575,0.0001008314,0.0007123523,0.0003506741,0.000001604976,0.000420986,0.001010768],"genre_scores_gemma":[0.3830781,0.00002066145,0.6150226,0.000947226,0.0003104988,0.00002943484,0.00001515586,0.00004545399,0.0005308657],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7791332,"threshold_uncertainty_score":0.9998861,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116635162","doi":"10.1155/asp/2006/26503","title":"Time Delay Estimation in Room Acoustic Environments: An Overview","year":2006,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":368,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Reverberation; Computer science; Sonar; Noise (video); Identification (biology); Ranging; Channel (broadcasting); Radar; Estimation; Acoustics; Telecommunications; Speech recognition; Real-time computing; Artificial intelligence; Engineering; Systems engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01511334718833428,"gpt":0.2898631340188438,"spread":0.2747497868305095,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007128933,0.0002462549,0.0002720112,0.0003637487,0.0002377837,0.0004762433,0.0006523758,0.00006813031,0.00003472335],"category_scores_gemma":[0.0000425754,0.000221333,0.00004555052,0.0006748519,0.00005388873,0.005836777,0.00005768585,0.0005363738,0.00004776716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002659365,"about_ca_system_score_gemma":0.0001121359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001753076,"about_ca_topic_score_gemma":0.00001041777,"domain_scores_codex":[0.9977608,0.0001456051,0.0006393846,0.0004254918,0.0005517905,0.0004769722],"domain_scores_gemma":[0.9991859,0.00008973088,0.0004118256,0.0001678557,0.00003313073,0.0001115113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002540714,0.000228565,0.0008676728,0.00004128409,0.000001364131,0.0002572088,0.0001409948,0.4118516,0.006606716,0.00005160915,0.00001132847,0.5799163],"study_design_scores_gemma":[0.001851526,0.0004923893,0.005786498,0.002451182,0.00001204565,0.0007764112,0.00008493947,0.9274047,0.01653373,0.04183657,0.001932152,0.0008378301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08424001,0.02340935,0.8906223,0.0002567287,0.0001452615,0.0001322976,7.817488e-7,0.00007214774,0.001121182],"genre_scores_gemma":[0.9311452,0.0003663018,0.06782506,0.0003986321,0.0001573028,0.000005788916,0.000002876664,0.00002201123,0.00007685341],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8469052,"threshold_uncertainty_score":0.9025699,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103636088","doi":"10.1109/lsp.2003.813679","title":"Speech probability distribution","year":2003,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":298,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Decorrelation; Generalized gamma distribution; Distribution (mathematics); Marginal distribution; Mathematics; Generalized integer gamma distribution; Speech processing; Speech recognition; Probability distribution; Multivariate statistics; Gaussian; Gamma distribution; Multivariate normal distribution; Joint probability distribution; Discrete cosine transform; Computer science; Random variable; Statistics; Artificial intelligence; Mathematical analysis; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01804183266396142,"gpt":0.2324819737331489,"spread":0.2144401410691875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005768498,0.0002164852,0.0001833769,0.00005823473,0.0003671476,0.0005276593,0.0005813432,0.0000702182,0.00001711584],"category_scores_gemma":[0.00006231927,0.0002005367,0.00007622961,0.0006520365,0.0001152195,0.001075912,0.00003430084,0.0002472724,0.00005568169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001272374,"about_ca_system_score_gemma":0.000185574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003947673,"about_ca_topic_score_gemma":9.25834e-7,"domain_scores_codex":[0.9980541,0.00009933966,0.0002900884,0.0005912965,0.0004378665,0.0005273426],"domain_scores_gemma":[0.9992315,0.00004418849,0.0001536482,0.0003182048,0.000116873,0.0001355525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001344843,0.0001937537,0.001860918,0.0002396395,0.00001845279,0.0001003937,0.0004105406,0.0007185754,0.4808607,0.0008887757,0.005330619,0.5093642],"study_design_scores_gemma":[0.0004396213,0.00004855947,0.0005865929,0.0001232565,0.00001223343,0.00014161,0.00001391932,0.003454244,0.9770061,0.01131987,0.006302535,0.000551411],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.167688,0.00014093,0.8288153,0.001867329,0.0002162329,0.0001262275,0.000001733291,0.0003115462,0.0008327315],"genre_scores_gemma":[0.9194753,0.000001028907,0.07819356,0.0021524,0.0001057702,0.00001378759,0.000003409973,0.00001276179,0.00004196817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7517873,"threshold_uncertainty_score":0.8177651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168729028","doi":"10.1109/tasl.2009.2025790","title":"On Optimal Frequency-Domain Multichannel Linear Filtering for Noise Reduction","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":288,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Noise reduction; Noise (video); Reduction (mathematics); Distortion (music); Filter (signal processing); Wiener filter; Computer science; Algorithm; Frequency domain; Mathematics; Speech recognition; Artificial intelligence; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.01224379360348507,"gpt":0.2637650849999195,"spread":0.2515212913964344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002956256,0.0002917891,0.0002469036,0.0002735714,0.000628639,0.0003104918,0.0003081639,0.0001241445,0.00001393326],"category_scores_gemma":[0.00002264985,0.0002746444,0.000104007,0.000393378,0.00005035501,0.0007730342,0.000002642692,0.0003090282,0.00001214919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007159231,"about_ca_system_score_gemma":0.00008187747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009035562,"about_ca_topic_score_gemma":0.000004763984,"domain_scores_codex":[0.9983085,0.00003459416,0.0002892139,0.0006324591,0.0002518455,0.0004833984],"domain_scores_gemma":[0.9992442,0.00006195591,0.0001276943,0.0002990272,0.00009268456,0.0001744584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000880334,0.0001721291,3.623156e-7,0.00007702665,0.00001295015,0.00003838903,0.002823845,0.002002043,0.2309443,0.00003647322,0.00003170408,0.7637727],"study_design_scores_gemma":[0.001139937,0.0005690096,0.00001213156,0.0003481044,0.00002193317,0.0002283799,0.0006085808,0.03601616,0.9588688,0.001688575,0.00003630075,0.0004621018],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.125054,0.0004396307,0.8726095,0.0007308995,0.0002654624,0.0002718896,0.000009368679,0.000338517,0.0002806684],"genre_scores_gemma":[0.6169182,0.00001593054,0.3823245,0.0003921373,0.0001360656,0.00002480978,0.000002202382,0.000017374,0.0001688108],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7633106,"threshold_uncertainty_score":0.9999706,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135817141","doi":"10.1109/tsa.2004.833008","title":"Time-Delay Estimation via Linear Interpolation and Cross Correlation","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":243,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Reverberation; Multilateration; Cross-correlation; Computer science; Microphone; Multipath propagation; Algorithm; Noise (video); Interpolation (computer graphics); SIGNAL (programming language); Linear interpolation; Speech recognition; Acoustics; Mathematics; Artificial intelligence; Telecommunications; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.00977493263216831,"gpt":0.2592749246945659,"spread":0.2494999920623976,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000222255,0.0002151025,0.0001799293,0.0002167874,0.0006763643,0.0004825004,0.000154932,0.0001278803,0.00001043686],"category_scores_gemma":[0.00001103621,0.0002085774,0.00004120218,0.000421548,0.000127841,0.001992737,0.000005065317,0.0002681527,0.00004632959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000063584,"about_ca_system_score_gemma":0.00009562495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001155642,"about_ca_topic_score_gemma":0.00000617812,"domain_scores_codex":[0.9986864,0.00002346707,0.0003026791,0.0004740678,0.0002437461,0.0002696589],"domain_scores_gemma":[0.9993818,0.00004059613,0.0001541614,0.0001766187,0.0001156417,0.0001311856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003090745,0.0000756051,0.0000445871,0.00006836484,0.0000111508,0.000009505977,0.0008818178,0.03281644,0.01526561,0.00001418732,0.000004409376,0.9507774],"study_design_scores_gemma":[0.001083634,0.0001796964,0.0002574124,0.0003266187,0.00002613151,0.000322175,0.00003147003,0.6955401,0.2984495,0.003368035,0.00004655374,0.0003686412],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1215976,0.0001900684,0.8770434,0.0004178616,0.0001626904,0.0001377892,0.000002062114,0.0002586098,0.0001898721],"genre_scores_gemma":[0.792267,0.00002423127,0.20729,0.0001922696,0.0000420605,0.000008916162,0.000002465971,0.00001557224,0.0001574498],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9504088,"threshold_uncertainty_score":0.8505538,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2000916836","doi":"10.1109/89.902276","title":"An adaptive KLT approach for speech enhancement","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Speech enhancement; Speech recognition; Noise (video); Computer science; Speech processing; White noise; Additive white Gaussian noise; Residual; Background noise; Colors of noise; Distortion (music); Mathematics; Artificial intelligence; Noise reduction; Algorithm; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.0278643172740081,"gpt":0.2735090793971463,"spread":0.2456447621231382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003793208,0.0003627032,0.000335007,0.0002605565,0.0009351995,0.0006181193,0.0005615515,0.0001427727,0.00001857756],"category_scores_gemma":[0.000005508647,0.0003378061,0.0001071528,0.0006636925,0.0001044215,0.001633546,0.00000481275,0.0002994943,0.00001142373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008298166,"about_ca_system_score_gemma":0.0001730986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001124649,"about_ca_topic_score_gemma":0.000009814531,"domain_scores_codex":[0.9975947,0.00004278183,0.0003680629,0.0009449812,0.0003884467,0.0006610174],"domain_scores_gemma":[0.9988582,0.00005173159,0.0001643899,0.0004325808,0.0002102553,0.0002828469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001182112,0.0004200063,0.00001136037,0.0000742198,0.00002453012,0.00001524419,0.0003972559,0.0005694503,0.02519102,0.00002886638,0.00005488005,0.9730949],"study_design_scores_gemma":[0.001139651,0.00086134,0.00001975301,0.00013081,0.00004352667,0.000253061,0.000312288,0.07282626,0.9212807,0.001520371,0.000997048,0.0006151238],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0130358,0.0003639641,0.983376,0.0003193186,0.0002137498,0.0004566971,0.00000691414,0.0003315542,0.001896022],"genre_scores_gemma":[0.5670416,0.00008143657,0.4317023,0.0004330243,0.0001100211,0.00008947783,0.000002854469,0.00002424589,0.0005149988],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9724798,"threshold_uncertainty_score":0.9999074,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2804619907","doi":"10.1145/3197517.3201292","title":"Visemenet","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":227,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Massachusetts; National Science Foundation","keywords":"Computer science; Computer facial animation; Viseme; Animation; Speech recognition; Motion (physics); Artificial intelligence; Motion capture; Synchronization (alternating current); Face (sociological concept); Computer animation; Speech synthesis; Computer graphics (images); Speech technology","retraction":null,"screen_n_in":null,"score":{"opus":0.02182020117249972,"gpt":0.2660231279796109,"spread":0.2442029268071111,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001027855,0.00009026991,0.00006818432,0.0001685351,0.0003400945,0.0001073293,0.0007656469,0.00005100388,0.00004921091],"category_scores_gemma":[0.00001248362,0.00008440942,0.00005784523,0.0007402137,0.00008676899,0.0003142305,0.000008178867,0.0001366334,0.0001369056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009877999,"about_ca_system_score_gemma":0.00003786772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005247682,"about_ca_topic_score_gemma":0.00002771639,"domain_scores_codex":[0.9992448,0.00001728441,0.0001060434,0.0002449212,0.0001866142,0.0002003203],"domain_scores_gemma":[0.9990891,0.00004700147,0.00002904049,0.0006815474,0.00007939835,0.00007389609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001858368,0.000298859,0.0002809627,0.00001715398,0.00006445382,0.00001226863,0.0008226868,0.0000453524,0.006913611,0.007915901,0.001953054,0.9816571],"study_design_scores_gemma":[0.0007702077,0.0007744542,0.002472782,0.00006745239,0.00002708327,0.00004747917,0.00004451981,0.003549055,0.812388,0.1253802,0.05388452,0.0005942679],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009109681,0.00003012892,0.9862418,0.002419757,0.0004038913,0.0000453483,0.00000170122,0.0002440445,0.001503695],"genre_scores_gemma":[0.8850074,0.00004013105,0.112231,0.002464537,0.00007385357,0.000008394962,4.624679e-7,0.000007955994,0.0001662855],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9810628,"threshold_uncertainty_score":0.3442116,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2054040518","doi":"10.1109/97.889636","title":"Wavelet speech enhancement based on the Teager energy operator","year":2001,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Energy operator; Speech enhancement; Wavelet; Speech recognition; Energy (signal processing); Computer science; Noise (video); A priori and a posteriori; Artificial intelligence; Pattern recognition (psychology); Noise measurement; Wavelet transform; Noise reduction; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01549480607661621,"gpt":0.2246815998051548,"spread":0.2091867937285386,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004590565,0.0002953041,0.000197022,0.0001395751,0.0005820969,0.0008272921,0.001163499,0.00006259501,0.0001269715],"category_scores_gemma":[0.0000199997,0.0002028164,0.00008676652,0.0006859229,0.0001084642,0.0005299971,0.0000606541,0.0002688213,0.00008011402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009442612,"about_ca_system_score_gemma":0.0001826879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000110228,"about_ca_topic_score_gemma":0.000001726728,"domain_scores_codex":[0.9976701,0.00009851775,0.0003004929,0.0006134377,0.0007145907,0.0006028363],"domain_scores_gemma":[0.9990395,0.0001243,0.0001546583,0.0004624606,0.00009533469,0.0001237376],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002656322,0.0001157563,0.00005232571,0.00002435913,0.00001334103,0.0001953788,0.0001856795,0.001092809,0.5174167,0.0000782535,0.01175327,0.4690455],"study_design_scores_gemma":[0.0003613874,0.00009100889,0.00003831231,0.0001979728,0.000007988145,0.00003033539,0.0000159403,0.09952317,0.8876404,0.0001973874,0.01150087,0.0003951978],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06252097,0.00009960493,0.9049305,0.02903893,0.0002777685,0.0001122222,8.543742e-7,0.0002053336,0.002813823],"genre_scores_gemma":[0.8881803,0.000003972725,0.01811329,0.09296055,0.0003783847,0.00003424762,0.000001360301,0.000025054,0.0003028294],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8868172,"threshold_uncertainty_score":0.8270614,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3197912330","doi":"10.21437/interspeech.2021-599","title":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Speech enhancement; Computer science; Speech recognition; Artificial intelligence; Noise reduction","retraction":null,"screen_n_in":null,"score":{"opus":0.01889896437997837,"gpt":0.277745182418337,"spread":0.2588462180383586,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002751997,0.00009238543,0.0001645317,0.0001976252,0.00007691907,0.00009545586,0.0004637132,0.0000426601,0.00007307166],"category_scores_gemma":[0.0001705538,0.00008114131,0.00007221808,0.00145265,0.00001472343,0.0008366661,0.0001664236,0.00004381101,0.000009343468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003695938,"about_ca_system_score_gemma":0.0001362788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001782014,"about_ca_topic_score_gemma":0.000008326439,"domain_scores_codex":[0.9989564,0.0000186243,0.0002069696,0.0003562095,0.0002353531,0.0002263792],"domain_scores_gemma":[0.9990039,0.0000732656,0.00009458612,0.0004037042,0.0003357946,0.00008870047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007607103,0.0001663849,0.00007339854,0.0000402393,0.00001754855,0.000004537415,0.00005995542,0.000002305246,0.5864092,0.0008445837,0.0006556853,0.4117186],"study_design_scores_gemma":[0.0004509249,0.0002220778,0.00008525584,0.000008756637,0.000008066583,0.000004500686,0.00006503679,0.005472445,0.9882699,0.0009335699,0.004370999,0.0001084857],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04783833,0.0002927719,0.94858,0.0005270033,0.0003463865,0.0001239394,0.00000179158,0.00006362697,0.002226161],"genre_scores_gemma":[0.3073774,0.00001670067,0.6906914,0.0003528167,0.00004458169,0.000005658306,0.000008012736,0.000005782459,0.001497699],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4116101,"threshold_uncertainty_score":0.3308847,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3161950572","doi":"10.1109/icassp39728.2021.9413740","title":"TSTNN: Two-Stage Transformer Based Neural Network for Speech Enhancement in the Time Domain","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Encoder; Computer science; Transformer; Speech recognition; Artificial neural network; Speech enhancement; Benchmark (surveying); Time domain; Pattern recognition (psychology); Artificial intelligence; Noise reduction; Computer vision; Engineering; Voltage","retraction":null,"screen_n_in":null,"score":{"opus":0.01613232171435938,"gpt":0.2649973294156781,"spread":0.2488650077013187,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005779989,0.0001201368,0.0001344872,0.00002865584,0.0001349078,0.000235413,0.0005373267,0.00002957009,0.0002356803],"category_scores_gemma":[0.00001113747,0.00008212026,0.00008193795,0.0004956922,0.0000195313,0.0002489035,0.00002576769,0.00009859358,0.00003046026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002412937,"about_ca_system_score_gemma":0.0001179896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007603115,"about_ca_topic_score_gemma":0.00008285474,"domain_scores_codex":[0.9987531,0.00006795929,0.0002057667,0.000313786,0.0002375395,0.0004219067],"domain_scores_gemma":[0.9993989,0.0001560383,0.00003580055,0.0003225165,0.00004380641,0.00004290733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001346078,0.0007968383,0.001010004,0.0001996666,0.00005650192,0.0005489076,0.002971113,0.01101428,0.1887357,0.01954081,0.02796655,0.747025],"study_design_scores_gemma":[0.002430344,0.0001653083,0.0002358289,0.00005759812,0.000008413822,0.00002636563,0.000159929,0.1567294,0.7881756,0.00779644,0.04380163,0.0004130534],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03905277,0.000167185,0.9394721,0.009769038,0.0001709569,0.0003042294,0.000001838928,0.00005630183,0.01100562],"genre_scores_gemma":[0.2316716,0.000005184185,0.7459075,0.01783003,0.0002842095,0.00009233312,0.00001826139,0.00001475239,0.004176093],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.746612,"threshold_uncertainty_score":0.3348767,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128604088","doi":"10.1109/tsa.2003.818031","title":"Incorporating the human hearing properties in the signal subspace approach for speech enhancement","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":171,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Speech recognition; Speech enhancement; Computer science; Signal subspace; Noise (video); Spectrogram; Noise reduction; Residual; Colors of noise; Subspace topology; Filter (signal processing); Artificial intelligence; Algorithm; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.04549423966659918,"gpt":0.264615521974624,"spread":0.2191212823080248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00126637,0.0002782925,0.0002364242,0.0001475058,0.001459964,0.0008763016,0.0005838064,0.00008160181,0.000004811769],"category_scores_gemma":[0.00001431458,0.0001699923,0.00007973565,0.0006894585,0.000150505,0.000706349,0.000005666936,0.0004567493,0.000003240756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006094757,"about_ca_system_score_gemma":0.0001602534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001816165,"about_ca_topic_score_gemma":0.00003265608,"domain_scores_codex":[0.9980316,0.0001366701,0.0003719706,0.0005565064,0.0003999976,0.000503276],"domain_scores_gemma":[0.9992371,0.0000924771,0.0001712705,0.0003330803,0.00009898572,0.00006706025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000497525,0.0008618046,0.0002763733,0.0006223466,0.00004931337,0.00002191987,0.008717634,0.004270592,0.1882878,0.0006155778,0.00009974187,0.7961271],"study_design_scores_gemma":[0.0006763074,0.0001655638,0.00003615661,0.0002165071,0.00002214748,0.0001326748,0.001626281,0.01169885,0.9832575,0.001575719,0.0002471553,0.0003450922],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07527658,0.0005098885,0.9207963,0.0007757731,0.00008050226,0.0006221168,9.41648e-7,0.00006916092,0.001868776],"genre_scores_gemma":[0.8915676,0.00001389429,0.1073569,0.0005280014,0.00005483505,0.0001273876,6.187314e-7,0.00001863472,0.0003320435],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8162911,"threshold_uncertainty_score":0.99984,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2600579021","doi":"10.1109/taslp.2017.2689681","title":"On the Design of Frequency-Invariant Beampatterns With Uniform Circular Microphone Arrays","year":2017,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":170,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"China Scholarship Council","keywords":"Directivity; Microphone; Superposition principle; Acoustics; White noise; Invariant (physics); Loudspeaker; Harmonics; Computer science; Mathematics; Control theory (sociology); Physics; Mathematical analysis; Telecommunications; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02053196319033007,"gpt":0.2443639679900176,"spread":0.2238320047996875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0004457347,0.0003064101,0.0003009595,0.0001645151,0.001359671,0.0007326665,0.00136073,0.0001014792,0.00004049297],"category_scores_gemma":[0.00006902127,0.0002006586,0.00007245011,0.0002635515,0.0002495984,0.0006986272,0.00001820046,0.0004125824,0.0000129362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004835068,"about_ca_system_score_gemma":0.0002162922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001188344,"about_ca_topic_score_gemma":0.00004581116,"domain_scores_codex":[0.9982958,0.00006266408,0.0002790946,0.0005346654,0.0004029538,0.0004248261],"domain_scores_gemma":[0.9979263,0.00015326,0.0003566208,0.001309204,0.0001220628,0.0001325741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001320324,0.0003385133,0.0001344645,0.0003129233,0.0001345077,0.0003349426,0.006647044,0.001413643,0.4676858,0.00007549173,0.00004583957,0.5227448],"study_design_scores_gemma":[0.0007695876,0.00031477,0.0002260184,0.0007035027,0.00004819079,0.0002082337,0.0005641651,0.002148585,0.9927409,0.001888981,0.00001452354,0.0003725658],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08184535,0.0004605819,0.9151837,0.001595561,0.0001226843,0.0002698007,0.000009547,0.0001030434,0.0004097001],"genre_scores_gemma":[0.8179757,0.00004411112,0.1812843,0.0004886065,0.00004985944,0.00002226793,8.607076e-7,0.00002548977,0.0001088189],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7361304,"threshold_uncertainty_score":0.9999404,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042809187","doi":"10.2307/3316063","title":"The historical functional linear model","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Bivariate analysis; Mathematics; Acceleration; Covariate; Function (biology); Basis (linear algebra); Functional data analysis; Applied mathematics; Calibration; Domain (mathematical analysis); Regression analysis; Linear regression; Basis function; Linear model; Statistics; Mathematical analysis; Geometry; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03208348061610872,"gpt":0.2109072855509716,"spread":0.1788238049348629,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002692112,0.00005142585,0.00006958435,0.00006343244,0.0003140196,0.0001158668,0.0002832236,0.00002245264,0.00001170239],"category_scores_gemma":[0.0004189392,0.0000371752,0.00002516555,0.0001189418,0.0000357418,0.0001291149,0.000004602749,0.0001643583,0.000007320657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000306501,"about_ca_system_score_gemma":0.002683238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006808143,"about_ca_topic_score_gemma":0.001147959,"domain_scores_codex":[0.9993607,0.00002256191,0.0001936007,0.0000585878,0.0001703143,0.0001942723],"domain_scores_gemma":[0.9990475,0.00009643351,0.0001156062,0.0001017135,0.0002706251,0.0003681632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005398453,0.00001616532,0.001116725,0.000009185534,0.00003580933,0.0004252042,0.0004365823,0.01223205,0.0001157556,0.4361837,0.463375,0.08604845],"study_design_scores_gemma":[0.0005167376,0.0001579125,0.0007104527,0.00002883648,0.00002243128,0.0009202781,0.00005468426,0.09641036,0.00124413,0.2266452,0.673004,0.000284904],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002435064,0.0006874199,0.9962932,0.0009415864,0.000816159,0.00001139522,0.00000560879,0.000002776146,0.0009983605],"genre_scores_gemma":[0.1294224,0.0000342355,0.8675426,0.0006309598,0.0001818033,4.816548e-7,5.01389e-7,0.000008532878,0.002178561],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.209629,"threshold_uncertainty_score":0.4759948,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036042055","doi":"10.1093/scan/nsu168","title":"Engaged listeners: shared neural processing of powerful political speeches","year":2015,"lang":"en","type":"article","venue":"Social Cognitive and Affective Neuroscience","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Institute of Mental Health","keywords":"Psychology; Politics; Communication; Cognitive psychology; Political science; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.07407495775601558,"gpt":0.320296329765696,"spread":0.2462213720096804,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006869212,0.0001807257,0.0002551784,0.0001141168,0.0005440342,0.00029173,0.0003763663,0.0000623882,0.000001042379],"category_scores_gemma":[0.002360764,0.0001642463,0.00006181214,0.0007445512,0.0007221464,0.001234376,0.0002828342,0.0003820119,0.000002643971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003494434,"about_ca_system_score_gemma":0.0002852499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001430133,"about_ca_topic_score_gemma":0.000002543234,"domain_scores_codex":[0.9979114,0.0004029554,0.00017233,0.0005660389,0.0004413488,0.0005059316],"domain_scores_gemma":[0.9988021,0.0003028472,0.0001401355,0.00008418283,0.0004151764,0.000255605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002455187,0.0006853733,0.01550133,0.0002656135,0.00002320442,0.0002631974,0.05435903,0.000004671462,0.3619401,0.0146707,0.0003186316,0.5517226],"study_design_scores_gemma":[0.003660752,0.002068569,0.1864583,0.0003646079,0.00007814218,0.0002224855,0.0242734,0.007209496,0.7404321,0.03361937,0.0002241994,0.001388654],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9505915,0.0001802219,0.04172714,0.000814407,0.0003006668,0.0002436564,0.00001568107,0.0001226993,0.006004039],"genre_scores_gemma":[0.9979375,0.000001539019,0.0009133019,0.000969847,0.000119711,0.000006017359,9.767416e-7,0.000009173907,0.00004193293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.550334,"threshold_uncertainty_score":0.669777,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100555417","doi":"10.1109/tsa.2003.815518","title":"A soft voice activity detector based on a laplacian-gaussian model","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Speech recognition; Hidden Markov model; Computer science; Noise (video); Discrete cosine transform; Gaussian; Posterior probability; Detector; Probability distribution; Bayesian probability; Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01821155687566045,"gpt":0.2488104677728221,"spread":0.2305989108971617,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003562593,0.0004161449,0.0003410943,0.0003604026,0.0009684105,0.000606284,0.0003944181,0.0001811622,0.00001700041],"category_scores_gemma":[0.00003084129,0.000384641,0.0001285001,0.0008248934,0.0001023885,0.001065649,0.000003197423,0.0005776856,0.00004160837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001086623,"about_ca_system_score_gemma":0.0004745297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000643068,"about_ca_topic_score_gemma":0.00002792386,"domain_scores_codex":[0.9975868,0.0000905393,0.0002765445,0.0008859347,0.0005015883,0.000658521],"domain_scores_gemma":[0.9988195,0.000116679,0.0001641525,0.0004837003,0.0001037627,0.000312175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001052111,0.000442681,0.0000225077,0.0001565473,0.00001928927,0.00004043981,0.0003032471,0.02477002,0.0367275,0.00002597224,0.00004330066,0.9373433],"study_design_scores_gemma":[0.0008085436,0.0001765064,0.00002471129,0.0002125749,0.00002254617,0.00005016376,0.00002105662,0.3254013,0.6719838,0.0005836834,0.0002773643,0.0004376633],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03208615,0.00009934748,0.9636335,0.0006842148,0.0002040632,0.0002058487,0.000008055456,0.0004141613,0.002664625],"genre_scores_gemma":[0.8911645,0.00001212378,0.1071054,0.001164386,0.00003347229,0.00003880147,3.377499e-7,0.00003498477,0.0004459763],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9369056,"threshold_uncertainty_score":0.9998605,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153038597","doi":"10.1109/msp.2014.2358871","title":"Objective Quality and Intelligibility Prediction for Users of Assistive Listening Devices: Advantages and limitations of existing tools","year":2015,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; Institut National de la Recherche Scientifique","funders":"National Institute on Deafness and Other Communication Disorders","keywords":"Reverberation; Intelligibility (philosophy); Active listening; Computer science; Speech perception; Speech recognition; Cochlear implant; Hearing aid; Perception; Sound quality; Audiology; Acoustics; Psychology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.195169606849618,"gpt":0.3647818179845549,"spread":0.169612211134937,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001087994,0.0001493484,0.0003099457,0.0001112023,0.0001413471,0.000139128,0.0001738377,0.0000616778,2.474678e-7],"category_scores_gemma":[0.001316384,0.000138536,0.0000371917,0.0003308686,0.0002165903,0.001255983,0.00007178822,0.0001070919,2.334159e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004098152,"about_ca_system_score_gemma":0.000277729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009528254,"about_ca_topic_score_gemma":0.00002097673,"domain_scores_codex":[0.9985906,0.00006079632,0.0005047054,0.000407468,0.0002500344,0.0001864071],"domain_scores_gemma":[0.9974009,0.0009693459,0.0005223491,0.0001319258,0.0008683168,0.000107184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002027357,0.0001262215,0.02321976,0.001390169,0.00004681596,0.000001663072,0.005723508,0.0004791585,0.07253768,0.0004120703,0.00003837347,0.8958218],"study_design_scores_gemma":[0.00385869,0.002058858,0.2051383,0.002853972,0.0002385334,0.00006886965,0.006004132,0.139331,0.6092873,0.0295561,0.0005470073,0.001057284],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2837692,0.0007841174,0.7138451,0.00008042934,0.00006267038,0.0002121455,0.00002432322,0.00006388008,0.001158155],"genre_scores_gemma":[0.8651604,0.00001190915,0.1346921,0.00003681149,0.00004243752,0.00001188632,0.00000473363,0.000008196779,0.0000315089],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8947645,"threshold_uncertainty_score":0.5649335,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1981446207","doi":"10.1155/s1110865703212014","title":"The Fusion of Distributed Microphone Arrays for Sound Localization","year":2003,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Microphone; Computer science; Noise-canceling microphone; Acoustic source localization; Microphone array; Acoustics; SIGNAL (programming language); Noise (video); Speech recognition; Sound (geography); Telecommunications; Artificial intelligence; Physics; Sound pressure","retraction":null,"screen_n_in":null,"score":{"opus":0.01377679451943762,"gpt":0.2795702934340798,"spread":0.2657934989146422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009216984,0.0001544864,0.0001922207,0.0001137279,0.0007289068,0.0003567957,0.0005083139,0.00004548762,0.000003620374],"category_scores_gemma":[0.0002896609,0.0001055692,0.00006680647,0.0006968147,0.00009604132,0.001102625,0.0000272183,0.0002573818,0.000001499931],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008276142,"about_ca_system_score_gemma":0.00016439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.619899e-7,"about_ca_topic_score_gemma":0.000002190801,"domain_scores_codex":[0.9984453,0.0001052988,0.0005227653,0.0002367776,0.0003421447,0.0003477318],"domain_scores_gemma":[0.9986644,0.0002776159,0.0005624865,0.0001334164,0.0002867758,0.00007525145],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000235011,0.000231325,0.002113716,0.0002008613,0.00001130513,0.00002742842,0.0006389811,0.05263875,0.04549658,0.002283462,0.0001446777,0.8959779],"study_design_scores_gemma":[0.002520945,0.0006280918,0.0001700676,0.001326143,0.00001441215,0.0003357049,0.0006411126,0.03477623,0.7242098,0.1978207,0.03700733,0.0005494935],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005603922,0.009937513,0.9835162,0.000206016,0.0002981778,0.0001174694,0.00000155101,0.00002129283,0.0002979004],"genre_scores_gemma":[0.9328276,0.0004797802,0.06637224,0.0001739761,0.0001045181,0.000006304349,0.000001554425,0.00001393246,0.00002010261],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9272237,"threshold_uncertainty_score":0.5606235,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1593114658","doi":"10.48550/arxiv.1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Parallelizable manifold; Computer science; Artificial intelligence; Layer (electronics); Class (philosophy); Machine learning; Deep learning; Space (punctuation); Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.0519460007582218,"gpt":0.2001051598742186,"spread":0.1481591591159968,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009688964,0.0001865111,0.0002680186,0.0003271474,0.0000757606,0.0000902355,0.001069595,0.0002068704,0.00003877952],"category_scores_gemma":[0.00008129789,0.0002094904,0.0001175251,0.0005934502,0.00006406643,0.000462604,0.001004521,0.0004475526,0.00001650435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000886124,"about_ca_system_score_gemma":0.0001253297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002845773,"about_ca_topic_score_gemma":0.00006517556,"domain_scores_codex":[0.9986582,0.0001103789,0.0001953105,0.0007032249,0.00008389787,0.0002489444],"domain_scores_gemma":[0.9987987,0.00008708351,0.0002735278,0.0006190072,0.0001316954,0.00008999735],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003740094,0.0003509262,0.1610221,0.0003708639,0.000156113,0.0006825674,0.01373159,0.7836535,0.006372743,0.01461906,0.0005045951,0.01849855],"study_design_scores_gemma":[0.001695872,0.0001290776,0.02958941,0.0007334128,0.00005822613,0.00001334394,0.002988125,0.8461757,0.03528305,0.08149463,0.000443326,0.001395789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6938456,0.0001018277,0.3037139,0.00006195863,0.0001604015,0.0001452468,0.000001017873,0.00009489921,0.001875119],"genre_scores_gemma":[0.9932358,0.00007422427,0.005799295,0.00002746891,0.00002497804,0.000001230878,0.000007417369,0.00000968309,0.0008199242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2993902,"threshold_uncertainty_score":0.854277,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4319596491","doi":"10.3390/electronics12040839","title":"Speech Emotion Recognition Based on Multiple Acoustic Features and Deep Convolutional Neural Network","year":2023,"lang":"en","type":"article","venue":"Electronics","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Mel-frequency cepstrum; Speech recognition; Computer science; Convolutional neural network; Feature (linguistics); Optimal distinctiveness theory; Pattern recognition (psychology); Artificial intelligence; Jitter; Feature extraction; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.01374466518818066,"gpt":0.2307959788309115,"spread":0.2170513136427309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002152659,0.0001098481,0.00008858148,0.0000829312,0.0002421004,0.0001290134,0.0001625738,0.00006446327,0.000006380365],"category_scores_gemma":[0.0001299087,0.0001080276,0.00003121597,0.000523413,0.00002318653,0.0001948298,0.00004235248,0.0002179566,0.00004251785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000662555,"about_ca_system_score_gemma":0.00008395079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000132678,"about_ca_topic_score_gemma":0.00003878709,"domain_scores_codex":[0.9989148,0.00004425968,0.0001015979,0.0002914932,0.0002183147,0.000429508],"domain_scores_gemma":[0.999478,0.0002124817,0.0000523952,0.0001440055,0.00005370455,0.00005945443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007526328,0.00007270429,0.002116479,0.00004667902,0.00001976743,0.00004432611,0.0001159605,0.09563881,0.009109438,0.000345836,0.006952974,0.8854617],"study_design_scores_gemma":[0.0004937727,0.0002055566,0.01667289,0.00003253797,0.000007533485,0.00003934546,0.000006481762,0.9670647,0.007763131,0.006851738,0.0006793782,0.0001829296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6734788,0.003845036,0.3160443,0.003421357,0.0009802198,0.0003846025,0.000006876844,0.001222254,0.0006164594],"genre_scores_gemma":[0.986816,0.0001180123,0.01176216,0.0008652484,0.0002659201,0.000009502996,0.00005414594,0.00001199196,0.0000969508],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8852788,"threshold_uncertainty_score":0.4405237,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100820878","doi":"10.1109/iros.2004.1389723","title":"Enhanced robot audition based on microphone array source separation with post-filter","year":2005,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Microphone array; Computer science; Filter (signal processing); Microphone; Robot; Noise-canceling microphone; Source separation; Acoustics; Separation (statistics); Speech recognition; Artificial intelligence; Computer vision; Physics; Sound pressure; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.01035412407496789,"gpt":0.2456421257564639,"spread":0.235288001681496,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000166261,0.0003675868,0.0002858786,0.0002117878,0.0001594907,0.0005440122,0.0007170189,0.000214006,0.000145144],"category_scores_gemma":[0.0000173411,0.0002935203,0.00009763652,0.0002300245,0.00003939382,0.0003298216,0.0001604326,0.0004663204,0.0002696559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001429729,"about_ca_system_score_gemma":0.0003125604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002136072,"about_ca_topic_score_gemma":0.00003659313,"domain_scores_codex":[0.9979287,0.00006107742,0.000282805,0.000920018,0.0004597454,0.000347595],"domain_scores_gemma":[0.9984339,0.00004798761,0.0003035385,0.0008639904,0.0002419677,0.000108558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008815702,0.0001810418,0.00001284003,0.00008026657,0.00002392654,0.000007071004,0.0003841709,0.1402516,0.8053933,0.00001354454,0.001197522,0.05236657],"study_design_scores_gemma":[0.0004185111,0.0001956243,0.0002868955,0.0003013536,0.00001074201,0.000006709869,0.000009817009,0.01424449,0.9833131,0.0001433679,0.0006166242,0.0004527866],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01320672,0.00003205311,0.9742355,0.004129692,0.0003155,0.000302093,0.000004186391,0.0004051095,0.007369155],"genre_scores_gemma":[0.5161629,0.000004127397,0.4778503,0.003618947,0.0003129224,0.00004479275,0.00007877757,0.00002277542,0.001904472],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5029562,"threshold_uncertainty_score":0.9999517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098651198","doi":"10.1109/tsmcb.2004.826398","title":"Enhanced Sound Localization","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Microphone; Reverberation; Acoustic source localization; Directivity; Acoustics; Orientation (vector space); Sound localization; Ranging; Microphone array; Computer science; Sound (geography); Noise-canceling microphone; Mathematics; Physics; Sound pressure; Telecommunications; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.01668988838778912,"gpt":0.2359552121620396,"spread":0.2192653237742505,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002423668,0.0003661323,0.0003470614,0.0002059663,0.0004002693,0.000628489,0.000481979,0.0002018041,0.00001990371],"category_scores_gemma":[0.000006637801,0.0003653058,0.000100085,0.0004829836,0.0001518524,0.0003327664,0.000008871963,0.0002876727,0.0002193406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001264929,"about_ca_system_score_gemma":0.000101105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009113752,"about_ca_topic_score_gemma":0.0001081326,"domain_scores_codex":[0.9975361,0.00008010317,0.0005448037,0.0007233838,0.0005353895,0.0005801755],"domain_scores_gemma":[0.9986323,0.00006558334,0.0001857821,0.0006403696,0.0001585452,0.0003174001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001490813,0.002191446,0.0001998649,0.000904253,0.0005389836,0.000162185,0.01291485,0.7424109,0.02177163,0.05323931,0.001740067,0.1637774],"study_design_scores_gemma":[0.006889295,0.001642885,0.0003433074,0.001586575,0.0002552076,0.0004875312,0.0009587809,0.05114966,0.8868001,0.02102642,0.02572914,0.003131174],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03331189,0.0005308027,0.9602667,0.0002285368,0.00143566,0.0003571589,0.0000086415,0.0003041009,0.003556489],"genre_scores_gemma":[0.9938855,0.0003096893,0.003072172,0.0003446616,0.0001508891,0.0000567506,0.000003167695,0.00004056315,0.002136649],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9605736,"threshold_uncertainty_score":0.9998799,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119901478","doi":"10.1109/tasl.2007.901310","title":"Soft Mask Methods for Single-Channel Speaker Separation","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Spectrogram; Computer science; SIGNAL (programming language); Speech recognition; Binary number; Channel (broadcasting); Masking (illustration); Source separation; Speech enhancement; Speech processing; Algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Telecommunications; Noise reduction","retraction":null,"screen_n_in":null,"score":{"opus":0.0249877122083876,"gpt":0.338796042543846,"spread":0.3138083303354585,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001204249,0.0002832343,0.0002669789,0.000303065,0.0005679628,0.0004490058,0.000303594,0.0001512383,0.00001613624],"category_scores_gemma":[0.00004120946,0.0002653122,0.0001107378,0.0005629688,0.00007058083,0.000915791,0.000004918836,0.0002557322,0.0000111304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007523395,"about_ca_system_score_gemma":0.00008536734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009532648,"about_ca_topic_score_gemma":0.00003845792,"domain_scores_codex":[0.9981645,0.00005492075,0.0003739533,0.0006087288,0.000221599,0.0005762791],"domain_scores_gemma":[0.9989428,0.000262182,0.0001673451,0.0002897312,0.0001349562,0.0002029913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000455872,0.00009436128,0.000001672359,0.0000907896,0.00001504428,0.00001670481,0.002151419,0.000149076,0.1478572,0.000007697869,0.00002192685,0.8495485],"study_design_scores_gemma":[0.0006465204,0.0001676969,0.00001009622,0.0001197743,0.00003534084,0.0001917828,0.0006148846,0.02307648,0.9734302,0.0006579249,0.0006709846,0.000378317],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003891847,0.001777765,0.9917343,0.0003449627,0.0004087129,0.0003061031,0.000004557144,0.0003910715,0.001140683],"genre_scores_gemma":[0.4624582,0.0000116736,0.5362429,0.0005573428,0.0001247781,0.00001907735,0.000002178727,0.00002568204,0.0005581373],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8491701,"threshold_uncertainty_score":0.9999799,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139129402","doi":"10.1109/robot.2004.1307286","title":"Localization of simultaneous moving sound sources for mobile robot using a frequency- domain steered beamformer approach","year":2004,"lang":"en","type":"preprint","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Mobile robot; Robot; Acoustic source localization; Frequency domain; Probabilistic logic; Computer vision; Complement (music); Artificial intelligence; Range (aeronautics); Beamforming; Acoustics; Sound (geography); Engineering; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.02598173886488693,"gpt":0.2722140111097762,"spread":0.2462322722448892,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003893653,0.0003920473,0.0005515048,0.0002478458,0.0002520551,0.0004376622,0.001149617,0.000353943,0.00001625677],"category_scores_gemma":[0.00007478846,0.0003613908,0.000217614,0.0003548629,0.0001067555,0.0003839085,0.0006763359,0.0002614823,0.000002541376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000250467,"about_ca_system_score_gemma":0.0006051101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002222368,"about_ca_topic_score_gemma":0.00001966039,"domain_scores_codex":[0.9974667,0.00004442858,0.0006684763,0.000877997,0.0004561323,0.0004862021],"domain_scores_gemma":[0.998127,0.0001468284,0.0005961881,0.0006925978,0.0003311452,0.0001061888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009129597,0.0001113517,0.00006506586,0.0008348498,0.00005297369,0.000002517476,0.00151088,0.9870404,0.003696795,0.0006980253,0.000002324089,0.005975663],"study_design_scores_gemma":[0.0006233894,0.0001059677,0.00000180542,0.0003995205,0.00004841107,0.00003541482,0.0005868187,0.8469343,0.03779522,0.1127637,0.00005856063,0.0006469275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03652053,0.0006645389,0.9602715,0.0000119544,0.0001956059,0.001020881,0.0000134999,0.0002106934,0.001090789],"genre_scores_gemma":[0.3593642,0.000004776579,0.6402961,0.00005246794,0.00008711265,0.00006248124,0.00002964765,0.0000275566,0.00007559129],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3228437,"threshold_uncertainty_score":0.9998838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109124605","doi":"10.1109/tpami.2003.1206512","title":"A graphical model for audiovisual object tracking","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Graphical model; Artificial intelligence; Video tracking; Computer vision; Exploit; Object (grammar); Tracking (education); Inference; Process (computing); Statistical model; Data modeling; Bayesian inference; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.03213946701149374,"gpt":0.2976170625537154,"spread":0.2654775955422217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003243466,0.0002068657,0.0002949864,0.0004686215,0.0003236564,0.0002187724,0.000313562,0.00006951409,0.00002496682],"category_scores_gemma":[0.00001205101,0.0001808279,0.0003456095,0.001028546,0.00005136567,0.0002910442,0.000002164649,0.0002094562,0.000004912203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000202983,"about_ca_system_score_gemma":0.00003963723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005124489,"about_ca_topic_score_gemma":0.0003791757,"domain_scores_codex":[0.9985466,0.00005176309,0.0003154053,0.0005577246,0.0002246599,0.0003038616],"domain_scores_gemma":[0.9992331,0.0001369335,0.00008224799,0.0003264155,0.0000851861,0.0001361424],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001109401,0.000191046,0.0003543918,0.00002434223,0.0003611559,0.000004692198,0.0004426762,0.07327027,0.001687012,0.0003559672,0.000005280554,0.923292],"study_design_scores_gemma":[0.00009337863,0.00007170879,0.00006449868,0.00001243757,0.0002138382,0.00001083247,0.0000187454,0.6460889,0.3513776,0.001830341,0.00001866395,0.0001990748],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003698068,0.0001231166,0.9955998,0.0001993864,0.0001034293,0.0001169916,0.00001580839,0.0000880347,0.00005537952],"genre_scores_gemma":[0.9764715,0.0001095611,0.02273766,0.0004958968,0.00001060989,0.00003359472,0.000001433638,0.0000109966,0.0001287782],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9728621,"threshold_uncertainty_score":0.737395,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2888493610","doi":"10.1109/taslp.2018.2862826","title":"Insights Into Frequency-Invariant Beamforming With Concentric Circular Microphone Arrays","year":2018,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Israel Science Foundation; National Natural Science Foundation of China","keywords":"Beamforming; Directivity; Invariant (physics); Microphone; Loudspeaker; Computer science; Acoustics; Physics; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.008513987475283591,"gpt":0.2308448052122166,"spread":0.222330817736933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001802855,0.0004062231,0.000362226,0.000316741,0.00116081,0.0006046775,0.0007672997,0.000153989,0.00004083492],"category_scores_gemma":[0.00003246006,0.000331013,0.00007427391,0.001358456,0.0003041136,0.001217467,0.00002044315,0.0004352662,0.00005167212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001237644,"about_ca_system_score_gemma":0.0003409285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001241168,"about_ca_topic_score_gemma":0.0001354498,"domain_scores_codex":[0.9976499,0.00005428594,0.0003706284,0.0008663291,0.0004484963,0.0006103395],"domain_scores_gemma":[0.998499,0.00006170209,0.0002090188,0.000707505,0.0002307368,0.000292028],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004161593,0.0001325419,0.00006392483,0.000186724,0.00005532791,0.0002937379,0.011082,0.00004815742,0.4459575,0.00001432298,0.00001540339,0.5421088],"study_design_scores_gemma":[0.001069141,0.0003482676,0.00006195714,0.0004858215,0.0000527474,0.0004344526,0.001020305,0.002051258,0.9923747,0.001173829,0.0003210018,0.000606499],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1900991,0.003385049,0.8048574,0.000371958,0.0002357259,0.0002056294,0.000002107861,0.0003273742,0.0005156345],"genre_scores_gemma":[0.663146,0.00005939208,0.3358509,0.0006191423,0.0001862173,0.00001771392,0.000002053201,0.00003003215,0.00008857279],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5464172,"threshold_uncertainty_score":0.9999142,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002786446","doi":"10.1121/1.4898429","title":"On the design and implementation of linear differential microphone arrays","year":2014,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Microphone array; Directivity; Computer science; Microphone; Beamforming; Acoustics; White noise; Noise (video); Short-time Fourier transform; SIGNAL (programming language); Sound pressure; Fourier transform; Mathematics; Telecommunications; Fourier analysis; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01230584599860526,"gpt":0.2558567051470595,"spread":0.2435508591484542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006541752,0.00007366676,0.0001624699,0.000008873417,0.0001809297,0.00002224273,0.0006377951,0.00002169735,0.00001520741],"category_scores_gemma":[0.0000985243,0.00003028407,0.0001306943,0.0001522324,0.0003071649,0.00005905822,0.0001406357,0.0001967408,7.510444e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001239479,"about_ca_system_score_gemma":0.00004427366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001070153,"about_ca_topic_score_gemma":6.992094e-8,"domain_scores_codex":[0.9990429,0.0001975321,0.0002561494,0.00006010533,0.0003190599,0.0001243019],"domain_scores_gemma":[0.9983479,0.0008639271,0.0004523768,0.0002048272,0.00009641988,0.00003450655],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007272818,0.00009166748,0.00004781384,0.00003061545,0.0001174256,1.593323e-7,0.002884254,0.003948491,0.8939685,0.00006074356,0.00889403,0.0898836],"study_design_scores_gemma":[0.0006894029,0.0008450209,0.001716886,0.0001006515,0.0001452256,0.00003499685,0.001463496,0.2306197,0.7552438,0.008861408,0.0001670577,0.0001124377],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09256907,0.0000443583,0.9009665,0.006266566,0.00008109665,0.00006025394,6.25808e-7,0.00000294298,0.000008612516],"genre_scores_gemma":[0.7991389,0.00008457654,0.1996421,0.001047091,0.00007780669,2.983001e-7,3.169641e-8,0.000003729274,0.000005521394],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7065698,"threshold_uncertainty_score":0.1391583,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119000949","doi":"10.1109/tsa.2005.858512","title":"On the importance of phase in human speech recognition","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Active listening; Phase (matter); Word error rate; Speech recognition; Computer science; Word (group theory); Mean squared error; Perception; Statistics; Noise (video); Pattern recognition (psychology); Mathematics; Artificial intelligence; Psychology; Physics; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.01647496210812098,"gpt":0.2745142636396765,"spread":0.2580393015315555,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004334586,0.0001964698,0.000210766,0.0002511315,0.0002973569,0.0001612296,0.000293806,0.00007992082,0.00006055387],"category_scores_gemma":[0.00001532341,0.0001520985,0.0000612443,0.0006736889,0.00009087165,0.0004671852,0.000003308127,0.0003271704,0.000008075729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004423487,"about_ca_system_score_gemma":0.0000588287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008312958,"about_ca_topic_score_gemma":0.0002802248,"domain_scores_codex":[0.9985969,0.0000610578,0.0003635611,0.0003974731,0.0002792669,0.0003017119],"domain_scores_gemma":[0.9993001,0.0001109937,0.000189346,0.0002842713,0.00006293476,0.00005239901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003458931,0.0004445572,0.00006736087,0.00007712554,0.000006949403,0.00008175899,0.0006173812,0.00006936082,0.09437306,0.00004694483,0.00007006425,0.9041108],"study_design_scores_gemma":[0.001027817,0.0001590897,0.0001047333,0.0003138886,0.00001213924,0.00005780655,0.0002513468,0.002041364,0.9922244,0.003567228,0.00001732998,0.0002228656],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7349913,0.0004450516,0.2620308,0.0004153784,0.00006194321,0.0001683965,0.000007805193,0.00009708505,0.001782274],"genre_scores_gemma":[0.9860427,0.00001262741,0.01326303,0.0004138151,0.00004849065,0.00001992067,0.000003242124,0.00001589731,0.000180316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.903888,"threshold_uncertainty_score":0.6202399,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2922332774","doi":"10.1109/icassp.2019.8683175","title":"Non-intrusive Speech Quality Assessment Using Neural Networks","year":2019,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"PESQ; Mean opinion score; Computer science; Mean squared error; Artificial neural network; Speech recognition; Quality (philosophy); Correlation; Quality of experience; Artificial intelligence; Machine learning; Speech enhancement; Quality of service; Statistics; Noise reduction; Telecommunications; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03097023443026254,"gpt":0.3260866942796873,"spread":0.2951164598494248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003696062,0.0001384295,0.000195661,0.00005088733,0.0001089785,0.0003411258,0.0006100122,0.00005935804,0.0001213561],"category_scores_gemma":[0.000008216534,0.0001158885,0.00006804502,0.0003304984,0.00001949194,0.0006982721,0.0003251023,0.0001859582,0.00005054088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007120345,"about_ca_system_score_gemma":0.00009009268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008633314,"about_ca_topic_score_gemma":0.000007728978,"domain_scores_codex":[0.9986453,0.00004158362,0.0002375848,0.0004056141,0.0002958036,0.000374081],"domain_scores_gemma":[0.9991388,0.00005736531,0.0001183996,0.0004996377,0.00008926043,0.00009657201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002634506,0.0002888339,0.2652771,0.0001316109,0.00009937392,0.0001248922,0.0005919145,0.06638083,0.06855799,0.01291525,0.00147438,0.5841315],"study_design_scores_gemma":[0.0003016856,0.00003766037,0.01571082,0.00001602017,0.000002943035,0.00002353067,0.00004546048,0.9689168,0.01395253,0.0006644733,0.000100128,0.0002279938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4685529,0.00001912533,0.5219061,0.0002655397,0.0005441972,0.0001048049,1.512264e-7,0.00009494222,0.008512201],"genre_scores_gemma":[0.8087536,0.000001317684,0.1896703,0.001076913,0.000117136,0.000001283971,8.793859e-7,0.000006594667,0.0003720406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9025359,"threshold_uncertainty_score":0.4725795,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111070087","doi":"10.1109/tasl.2007.904233","title":"Single-Channel Speech Separation Using Soft Mask Filtering","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Wiener filter; Filter (signal processing); Binary number; Channel (broadcasting); Computer science; Minimum mean square error; Gaussian; Algorithm; Noise (video); Mean squared error; Signal-to-noise ratio (imaging); Speech enhancement; Mathematics; Speech recognition; Statistics; Artificial intelligence; Physics; Telecommunications; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.02335064070139286,"gpt":0.2833091741114335,"spread":0.2599585334100406,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007026731,0.0003732067,0.0003075924,0.0004498953,0.0007373553,0.0006641734,0.0003880907,0.0001794544,0.00003123884],"category_scores_gemma":[0.00002165404,0.0003717618,0.0001026003,0.0008326411,0.00009100833,0.001443628,0.00001129351,0.0004185908,0.00002163075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001447208,"about_ca_system_score_gemma":0.0001121095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004547394,"about_ca_topic_score_gemma":0.0001230158,"domain_scores_codex":[0.9975877,0.00004693306,0.0004601665,0.0007202051,0.0004485486,0.0007364516],"domain_scores_gemma":[0.9989394,0.0001002255,0.0002133196,0.0003691001,0.0001179892,0.0002599966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003008407,0.00009538253,0.000008511499,0.0000979183,0.00001445324,0.0001465885,0.001909473,0.0006155124,0.3002458,0.000001816117,0.000008053577,0.6968264],"study_design_scores_gemma":[0.0004997498,0.0001079607,0.00002006106,0.0002678996,0.00003107489,0.0006340111,0.0008704001,0.04120684,0.9556333,0.0001516374,0.00009973169,0.0004773602],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1796896,0.0009397702,0.8177185,0.0001182295,0.0003672813,0.0001634739,0.000003814985,0.0004205713,0.0005787996],"genre_scores_gemma":[0.818491,0.00001737384,0.1804781,0.0004291136,0.0001812837,0.000005072012,0.00000186632,0.00003736439,0.0003589096],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.696349,"threshold_uncertainty_score":0.9998735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147271331","doi":"10.1109/tsmcb.2004.830345","title":"Phase-Based Dual-Microphone Robust Speech Enhancement","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Speech recognition; Reverberation; Microphone; Speech enhancement; Word error rate; Beamforming; Multilateration; Noise (video); SIGNAL (programming language); Pattern recognition (psychology); Artificial intelligence; Acoustics; Noise reduction; Telecommunications; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.02311683342707415,"gpt":0.246703202702189,"spread":0.2235863692751149,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003868071,0.0005417671,0.0005178405,0.0002980847,0.0004352208,0.0006909859,0.0005687081,0.0002273843,0.00005850325],"category_scores_gemma":[0.000005440224,0.0005401725,0.0001624503,0.000584531,0.0002008339,0.0002514503,0.00001217271,0.0004410746,0.0003453068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002131263,"about_ca_system_score_gemma":0.0002376037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001668439,"about_ca_topic_score_gemma":0.00008716983,"domain_scores_codex":[0.9965205,0.0001044858,0.0007689252,0.0009980836,0.0007548594,0.00085317],"domain_scores_gemma":[0.9980807,0.00008621746,0.0002638078,0.000927946,0.0001865499,0.0004547488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004827336,0.01515185,0.00006630569,0.00144014,0.0008855797,0.001093089,0.005643362,0.338718,0.3104627,0.005075395,0.006108684,0.3148721],"study_design_scores_gemma":[0.006538367,0.001414742,0.00001716815,0.0006342691,0.00009781283,0.0002021855,0.0001402977,0.01057701,0.9636245,0.0003772708,0.01536248,0.001013877],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09856103,0.0008241516,0.8951771,0.0006189765,0.001915181,0.0005893472,0.00002642188,0.0002935388,0.00199431],"genre_scores_gemma":[0.9718755,0.0003088054,0.02379565,0.000508368,0.0002096427,0.00009721679,0.000007029984,0.00006079629,0.003136919],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8733146,"threshold_uncertainty_score":0.999705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140651276","doi":"10.1109/tasl.2006.883253","title":"Single-Ended Speech Quality Measurement Using Machine Learning Methods","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"PESQ; Computer science; Speech recognition; Support vector machine; Mean opinion score; Random forest; Artificial intelligence; Classifier (UML); Multiplicative function; Machine learning; Pattern recognition (psychology); Speech enhancement; Noise reduction; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04909807463381612,"gpt":0.3245484020317244,"spread":0.2754503273979083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002049124,0.0004432938,0.0004684341,0.0003749838,0.0009792242,0.0007683134,0.0004437272,0.0001694256,0.00003768285],"category_scores_gemma":[0.00006263044,0.0004183023,0.0001518928,0.0009089799,0.0001113039,0.0009552132,0.00001335858,0.000677627,0.00001043854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002552658,"about_ca_system_score_gemma":0.000181693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005145553,"about_ca_topic_score_gemma":0.0002956989,"domain_scores_codex":[0.9966024,0.0004236496,0.0006188122,0.000867126,0.0007913233,0.0006967255],"domain_scores_gemma":[0.998683,0.0001217264,0.0003347209,0.0004135826,0.0002489056,0.0001980261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002129257,0.0001608548,0.00004684485,0.0001024883,0.00001849751,0.00004117043,0.0004463812,0.0004650512,0.3710366,0.000006179352,0.000004849236,0.6276498],"study_design_scores_gemma":[0.0007359767,0.00008687354,0.00006925283,0.0002185698,0.00005085565,0.0002488742,0.0002875079,0.04059317,0.9564943,0.0003422442,0.0003202191,0.0005521642],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04936249,0.004363513,0.9436553,0.0002376476,0.0002635846,0.0001964178,0.000004395821,0.0006036418,0.001313004],"genre_scores_gemma":[0.5455788,0.0000152644,0.4538116,0.0001730407,0.00009649552,0.000007899417,0.000001771962,0.00003046698,0.000284556],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6270976,"threshold_uncertainty_score":0.9998269,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2507780144","doi":"10.1109/mcas.2016.2583681","title":"Recent Developments in Speech Enhancement in the Short-Time Fourier Transform Domain","year":2016,"lang":"en","type":"article","venue":"IEEE Circuits and Systems Magazine","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Université de Sherbrooke; Concordia University","funders":"","keywords":"Short-time Fourier transform; Speech enhancement; Estimator; Computer science; Spectral density estimation; Wiener filter; Noise (video); Gaussian noise; Speech recognition; Fourier transform; Frequency domain; Algorithm; Spectral density; Noise reduction; Artificial intelligence; Mathematics; Fourier analysis; Statistics; Telecommunications; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.02387619114841635,"gpt":0.2448962645437055,"spread":0.2210200733952891,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001301716,0.0001730814,0.0002468913,0.0001467804,0.00007331562,0.0001823467,0.0004938773,0.00006424927,0.00001161888],"category_scores_gemma":[0.00001525798,0.00009713475,0.00002287271,0.0004311751,0.00003309103,0.0003781994,0.0000288142,0.00009541958,0.00008431458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001076278,"about_ca_system_score_gemma":0.00008333054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005914549,"about_ca_topic_score_gemma":0.00005565177,"domain_scores_codex":[0.9982222,0.00009897952,0.0004526394,0.0003948484,0.0004053723,0.0004259962],"domain_scores_gemma":[0.9994538,0.00007181089,0.00005968101,0.0002936441,0.00004853679,0.00007246113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003437846,0.00006133209,0.001382007,0.00003523412,0.000007367692,0.00009792448,0.00113204,0.000001537761,0.03917048,0.0001274337,0.0005395107,0.9574417],"study_design_scores_gemma":[0.0121972,0.0008205869,0.06312194,0.005876894,0.00003013913,0.001644642,0.0007389912,0.004145057,0.2109599,0.008974535,0.6880079,0.003482204],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7695323,0.002690308,0.19002,0.004851721,0.00123847,0.001416947,0.000006281151,0.00008841482,0.03015561],"genre_scores_gemma":[0.996568,0.0004132109,0.001417224,0.0002696872,0.00009342837,0.00007430298,0.000001084588,0.00001085876,0.001152168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9539595,"threshold_uncertainty_score":0.396104,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139231522","doi":"10.1109/icapr.2009.80","title":"Bangla Speech Recognition System Using LPC and ANN","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"La Cité Collégiale","funders":"","keywords":"Speech recognition; Computer science; Linear predictive coding; Cepstrum; Speech processing; Voice activity detection; Speech coding; Mel-frequency cepstrum; Artificial intelligence; Pattern recognition (psychology); Vector quantization; Artificial neural network; Feature extraction; Feature vector","retraction":null,"screen_n_in":null,"score":{"opus":0.02663728876712292,"gpt":0.24343624757153,"spread":0.216798958804407,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000137672,0.0000689445,0.00007948931,0.00005984966,0.0001047947,0.0002283042,0.0001377513,0.00003386264,0.000005263509],"category_scores_gemma":[0.0000100163,0.00005935723,0.00001594229,0.000199243,0.000009189207,0.0005917532,0.00003293391,0.00004536307,0.00002458656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002451978,"about_ca_system_score_gemma":0.0000220888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006895209,"about_ca_topic_score_gemma":0.000001167351,"domain_scores_codex":[0.9994088,0.00001555358,0.0001023359,0.0002069618,0.0001114993,0.0001548532],"domain_scores_gemma":[0.9997107,0.00001220109,0.00003852086,0.0001319523,0.00004712635,0.00005952513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000130427,0.000009607021,0.0001062932,0.00001601418,0.000001744647,0.00002578695,0.00005808715,0.000001616335,0.01113097,0.0002279392,0.0001357971,0.9882848],"study_design_scores_gemma":[0.0005383174,0.0001377376,0.002306107,0.000305834,0.00001222682,0.0009712225,0.0001459013,0.04770812,0.938187,0.008774316,0.0004913069,0.0004218837],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5935832,0.0003704563,0.3802464,0.0006122317,0.0001858795,0.00009660959,6.429832e-7,0.0004374285,0.02446713],"genre_scores_gemma":[0.7019288,0.000003090265,0.2975121,0.0003999893,0.00006953746,3.374861e-7,5.852105e-7,0.000002266843,0.00008335274],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9878629,"threshold_uncertainty_score":0.2420517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4311167834","doi":"10.1109/taslp.2022.3205757","title":"Deep Learning-Based Non-Intrusive Multi-Objective Speech Assessment Model With Cross-Domain Features","year":2022,"lang":"en","type":"article","venue":"IEEE/ACM Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"National Science and Technology Council; Academia Sinica","keywords":"PESQ; Computer science; Intelligibility (philosophy); Speech recognition; Artificial neural network; Mean opinion score; Artificial intelligence; Machine learning; Metric (unit); Speech enhancement; Noise reduction; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.009114245931778077,"gpt":0.2788869952743462,"spread":0.2697727493425682,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0005143661,0.0005129732,0.0004420311,0.0004622412,0.002560855,0.0008786725,0.0009422494,0.0001248346,0.00007829435],"category_scores_gemma":[0.00002894024,0.0004647738,0.0001359735,0.00109788,0.000189109,0.0008386531,0.00005752624,0.001492378,0.000006653183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003457799,"about_ca_system_score_gemma":0.0006363424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007434014,"about_ca_topic_score_gemma":0.0001684958,"domain_scores_codex":[0.9967197,0.0001525608,0.0003636063,0.001136216,0.000856564,0.0007713234],"domain_scores_gemma":[0.9984499,0.0001245348,0.0003093291,0.0006347917,0.0002154518,0.0002659998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002434215,0.0005697914,0.000441402,0.0001745792,0.00008432368,0.0005295145,0.00770393,0.4081535,0.01509393,0.000005285305,0.00002006744,0.5669802],"study_design_scores_gemma":[0.004511361,0.0009572093,0.001201334,0.0002264408,0.00008629855,0.0007046593,0.005360958,0.7240615,0.2610794,0.0004312795,0.0001094002,0.001270104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09128759,0.0006942142,0.9059821,0.0005236342,0.0001584803,0.0004231373,0.00001697472,0.000426497,0.0004873913],"genre_scores_gemma":[0.6097332,0.000009175687,0.3886679,0.0006248733,0.00004473919,0.0001271126,0.000008328416,0.00004687219,0.0007379195],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5657102,"threshold_uncertainty_score":0.9997804,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028124797","doi":"10.1016/j.specom.2012.08.007","title":"Multitaper MFCC and PLP features for speaker verification using i-vectors","year":2012,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal; Institut National de la Recherche Scientifique","funders":"National Institute of Standards and Technology","keywords":"Multitaper; Mel-frequency cepstrum; Computer science; NIST; Speech recognition; Pattern recognition (psychology); Cepstrum; Speaker recognition; Artificial intelligence; Feature extraction","retraction":null,"screen_n_in":null,"score":{"opus":0.03390941946555964,"gpt":0.2998207171212208,"spread":0.2659112976556612,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004597358,0.0001083353,0.0001031612,0.00007493769,0.0003213752,0.0001706121,0.0005189822,0.00007100602,0.000003573621],"category_scores_gemma":[0.0001086791,0.0001040842,0.00003349165,0.0001929404,0.00005046402,0.001112449,0.0001781457,0.0001097535,0.000009183477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005753657,"about_ca_system_score_gemma":0.0000283453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004873599,"about_ca_topic_score_gemma":0.0000153378,"domain_scores_codex":[0.999227,0.00006168074,0.0001560482,0.0001778505,0.0001349128,0.000242503],"domain_scores_gemma":[0.9988203,0.0001109446,0.0001183012,0.0007661422,0.0001065934,0.00007772683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003460749,0.0002884244,0.02377885,0.0001141171,0.00005454465,3.674055e-7,0.005978219,0.00007099264,0.2235007,0.01563733,0.002087479,0.7284544],"study_design_scores_gemma":[0.001417461,0.0000827648,0.1169945,0.0001886491,0.00006567688,0.0001346788,0.0004649513,0.02426201,0.8029146,0.007589765,0.04495444,0.0009304811],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5740828,0.007384897,0.4129843,0.002054519,0.0003934902,0.0006151833,0.000004217732,0.0002853486,0.002195247],"genre_scores_gemma":[0.5863629,0.0000678771,0.4132913,0.0001322102,0.00004847722,0.00001142097,0.00001008807,0.000008191956,0.0000675437],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7275239,"threshold_uncertainty_score":0.4244431,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2560525638","doi":"10.3758/s13428-016-0830-1","title":"Chronset: An automated tool for detecting speech onset","year":2016,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"The Scarborough Hospital","funders":"","keywords":"Multitaper; Computer science; Speech recognition; Measure (data warehouse); Artificial intelligence; Natural language processing; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.2584792315470756,"gpt":0.5748492312116953,"spread":0.3163699996646197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01124919,0.000179516,0.0002316605,0.0003913275,0.0006299706,0.0004691826,0.00148846,0.0001351933,0.00005428],"category_scores_gemma":[0.002583198,0.0001273074,0.0000951832,0.0008674181,0.0001653152,0.0009791908,0.0004163348,0.0002721785,0.00005035716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000191284,"about_ca_system_score_gemma":0.0004011141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003088256,"about_ca_topic_score_gemma":0.00001263635,"domain_scores_codex":[0.9957505,0.001442136,0.0003248459,0.0007607306,0.0006592491,0.001062511],"domain_scores_gemma":[0.9963647,0.001749454,0.00008242207,0.001005035,0.0005258739,0.0002724918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001144013,0.00005659082,0.0006863081,0.00001062757,0.00000292464,0.0000223006,0.00007749016,1.151931e-7,0.3517207,0.00004275428,0.0002772113,0.6470915],"study_design_scores_gemma":[0.000609931,0.0003957698,0.007362662,0.00007162667,0.000006128614,0.0001045739,0.00004039179,0.002324277,0.9841607,0.001828025,0.00283076,0.0002651287],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3424472,0.00006405921,0.6554424,0.0004413371,0.0001814989,0.0005476732,0.00001080421,0.0007877827,0.0000772892],"genre_scores_gemma":[0.1170463,0.000005180058,0.881802,0.0000441158,0.000116906,0.0003901138,0.000001926036,0.00003150584,0.0005619811],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6468264,"threshold_uncertainty_score":0.5191444,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130121545","doi":"10.1109/tsp.2008.2010596","title":"On Spatial Aliasing in Microphone Arrays","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Signal Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Aliasing; Narrowband; Wideband; Microphone array; Acoustics; Computer science; Broadband; Bandlimiting; Microphone; Direction finding; Direction of arrival; Spatial filter; Algorithm; Mathematics; Fourier transform; Filter (signal processing); Telecommunications; Optics; Physics; Antenna (radio); Mathematical analysis; Loudspeaker; Computer vision; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02176814778197394,"gpt":0.2386615811167431,"spread":0.2168934333347692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001731511,0.0002442668,0.0002342922,0.0003976639,0.0006159188,0.0001755696,0.0004391735,0.0001021255,0.00003814128],"category_scores_gemma":[0.00000436541,0.0002404223,0.00008602664,0.0008658836,0.00009043788,0.000717378,0.000002487928,0.0004751965,0.00008917767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001255331,"about_ca_system_score_gemma":0.000244468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004637191,"about_ca_topic_score_gemma":0.00002624956,"domain_scores_codex":[0.9981951,0.00005570497,0.0003394541,0.0005553859,0.000401617,0.0004528045],"domain_scores_gemma":[0.9993731,0.00008741459,0.0001096547,0.0002389214,0.00007246073,0.0001183939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001157541,0.0005260961,0.00004089175,0.00005816031,0.00001167592,0.0002439799,0.002200712,0.03745365,0.1783629,0.000008700717,0.00006347165,0.780914],"study_design_scores_gemma":[0.0007985145,0.0001693704,0.0001089465,0.0003362425,0.000005372834,0.0001511407,0.000039868,0.02867675,0.9686298,0.0006671465,0.00006076039,0.0003560849],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08626449,0.00009381184,0.9121245,0.0002818136,0.0002446982,0.0001015558,0.00000148326,0.0001966918,0.0006909563],"genre_scores_gemma":[0.9638624,0.00001296478,0.03523919,0.0006454769,0.00007135151,0.00001476065,4.568277e-7,0.0000231066,0.0001302405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8775979,"threshold_uncertainty_score":0.9804136,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2019338151","doi":"10.1121/1.1787525","title":"Measurements of directional properties of reverberant sound fields in rooms using a spherical microphone array","year":2004,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Microstructural Sciences; University of Waterloo","funders":"University of Waterloo","keywords":"Acoustics; Reverberation; Sound energy; Microphone; Reverberation room; Microphone array; Anisotropy; Isotropy; Impulse (physics); Attenuation; Physics; Optics; Sound pressure; Sound (geography)","retraction":null,"screen_n_in":null,"score":{"opus":0.03633421389483735,"gpt":0.251627352135803,"spread":0.2152931382409656,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005812593,0.00009437648,0.0003171579,0.00001688069,0.0000829338,0.0000127597,0.0007103513,0.00004694952,0.000005296762],"category_scores_gemma":[0.0001547927,0.00004978619,0.0002427746,0.0004336916,0.0004349534,0.0001339522,0.0001248465,0.0002821067,2.62393e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009547744,"about_ca_system_score_gemma":0.0002457379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001629517,"about_ca_topic_score_gemma":0.000002064753,"domain_scores_codex":[0.9985344,0.00009408372,0.0005160623,0.00008154091,0.0006044475,0.0001694598],"domain_scores_gemma":[0.9989433,0.00008027766,0.0005112712,0.0001962391,0.0002288287,0.00004007053],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006708245,0.0001855007,0.0004034071,0.0000515747,0.00006714477,4.089438e-7,0.001425684,0.07401774,0.9216307,1.402431e-7,0.00006995388,0.00208069],"study_design_scores_gemma":[0.000511838,0.0001659135,0.0006966312,0.000432139,0.00005288307,0.00006744933,0.0003976378,0.005090729,0.9913491,0.001155271,0.000006304711,0.00007409924],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2961238,0.0004965418,0.7019928,0.001208999,0.0001104355,0.00004725831,4.176007e-7,0.000002468112,0.00001735666],"genre_scores_gemma":[0.6553893,0.0000383758,0.3443026,0.0002240563,0.00003766598,1.809907e-7,1.100321e-8,0.000003465169,0.000004342892],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3592655,"threshold_uncertainty_score":0.2030222,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155213659","doi":"10.1109/lsp.2006.884038","title":"Time Delay Estimation via Minimum Entropy","year":2007,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Multilateration; Computer science; Algorithm; Reverberation; Entropy (arrow of time); Additive white Gaussian noise; Gaussian; Speech recognition; White noise; Mathematics; Telecommunications; Acoustics","retraction":null,"screen_n_in":null,"score":{"opus":0.008847824756960781,"gpt":0.2346610019047672,"spread":0.2258131771478064,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005988018,0.0002309829,0.0001895787,0.0002132101,0.0003311218,0.0004237995,0.0006923579,0.00008018998,0.00002245976],"category_scores_gemma":[0.00001671772,0.0002210462,0.00007077041,0.0005793686,0.0001150861,0.00129053,0.00005308701,0.0002172087,0.0002822924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000937101,"about_ca_system_score_gemma":0.00008737024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003462431,"about_ca_topic_score_gemma":5.442751e-7,"domain_scores_codex":[0.9979805,0.00003094591,0.0003669406,0.0004903639,0.0005121585,0.0006191318],"domain_scores_gemma":[0.9991957,0.00008580268,0.0002245432,0.0002367848,0.00009308472,0.0001640706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001253427,0.00002904365,0.00003547233,0.00003297691,0.000007490949,0.00008493343,0.0004051148,0.001371033,0.6389084,0.000005948435,0.001414711,0.3576924],"study_design_scores_gemma":[0.0004223866,0.00005696635,0.0001535102,0.0001323757,0.00001498747,0.0001437605,0.00001109405,0.3181016,0.6791296,0.0008401362,0.0005458945,0.0004477453],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1431946,0.0001211145,0.8538158,0.001933726,0.000191951,0.00008725709,3.519976e-7,0.0003395428,0.0003156047],"genre_scores_gemma":[0.8223228,4.744019e-7,0.1723057,0.004981521,0.0002777075,0.000003905926,0.000002933011,0.00002042849,0.00008447359],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6815101,"threshold_uncertainty_score":0.9014004,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2885194458","doi":"10.1177/0956797618779083","title":"Familiar Voices Are More Intelligible, Even if They Are Not Recognized as Familiar","year":2018,"lang":"en","type":"article","venue":"Psychological Science","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Industry Canada","keywords":"Psychology; Intelligibility (philosophy); Perception; Vocal tract; Cognitive psychology; Speech perception; Communication; Speech recognition; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.04582410819481825,"gpt":0.3623059346435138,"spread":0.3164818264486955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001418118,0.0003035208,0.0003325714,0.0002036428,0.0008046276,0.0006505326,0.004394446,0.0001557813,0.00009471693],"category_scores_gemma":[0.001187766,0.0002077568,0.0001075025,0.002110817,0.001508299,0.001357156,0.0007075373,0.0003518621,0.001591519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006943189,"about_ca_system_score_gemma":0.0000788855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004309691,"about_ca_topic_score_gemma":0.00001892095,"domain_scores_codex":[0.9958763,0.00009238589,0.0003913976,0.001631136,0.001033309,0.0009754396],"domain_scores_gemma":[0.9976329,0.0001638569,0.0003226445,0.001030344,0.0004328196,0.0004174861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001704833,0.0008728154,0.014363,0.00003579971,0.00002063164,0.0002043113,0.00311776,0.00002206738,0.1223804,0.001909166,0.004754527,0.852149],"study_design_scores_gemma":[0.001395012,0.001516509,0.5703129,0.0004707273,0.00001953223,0.0002754719,0.001424249,0.005566888,0.3236966,0.07508191,0.01837733,0.001862869],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9084661,0.00008963796,0.04389643,0.006900778,0.001582234,0.0003075257,0.000005579008,0.0006345218,0.0381172],"genre_scores_gemma":[0.957466,0.0001207458,0.03542183,0.006273226,0.0002725283,0.00001976898,5.05123e-7,0.00000926548,0.0004161196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8502862,"threshold_uncertainty_score":0.9991859,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4283818626","doi":"10.1609/aaai.v36i2.20102","title":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Leverage (statistics); Speech recognition; Synchronization (alternating current); Visualization; Artificial intelligence; Sound quality; Audio visual; Representation (politics); Face (sociological concept); Computer vision; Multimedia; Channel (broadcasting)","retraction":null,"screen_n_in":null,"score":{"opus":0.05082625186549095,"gpt":0.260706983795317,"spread":0.209880731929826,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007938362,0.0003143403,0.0003148079,0.0001891749,0.001002516,0.0004999971,0.002331966,0.00006407281,0.0001211872],"category_scores_gemma":[0.000185384,0.0002459309,0.0001083203,0.001180161,0.0001911227,0.0008815199,0.000881904,0.0005537141,0.00003319046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001571962,"about_ca_system_score_gemma":0.0002298807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003463538,"about_ca_topic_score_gemma":0.00001199122,"domain_scores_codex":[0.9970704,0.00003962377,0.000556791,0.0007771912,0.001053161,0.0005027855],"domain_scores_gemma":[0.9983081,0.00006829525,0.0006203408,0.0003964318,0.0004918418,0.0001149686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001056339,0.0002177992,0.0002482994,0.00007265152,0.0000352541,0.000005425434,0.004904864,0.005576788,0.625535,0.02922842,0.000232113,0.3338378],"study_design_scores_gemma":[0.00004421955,0.0002953182,0.00004140847,0.0001333772,0.00001581437,0.00005503454,0.001155835,0.1167503,0.8715265,0.009585097,0.00007934584,0.0003177139],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6947783,0.0001268955,0.2899028,0.004024602,0.001012931,0.0008945751,0.000007032699,0.0003103406,0.00894253],"genre_scores_gemma":[0.9893633,0.00001236832,0.009641468,0.0002914218,0.0001343536,0.00009161944,0.000001235669,0.00002440025,0.0004398728],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3335201,"threshold_uncertainty_score":0.9999993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128977628","doi":"10.1109/aspaa.2007.4392978","title":"Broadband Music: Opportunities and Challenges for Multiple Source Localization","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Broadband; Narrowband; Computer science; Multiple signal classification; Beamforming; Subspace topology; Microphone; SIGNAL (programming language); Signal subspace; Parameterized complexity; Microphone array; Algorithm; Acoustics; Speech recognition; Artificial intelligence; Telecommunications; Physics; Noise (video)","retraction":null,"screen_n_in":null,"score":{"opus":0.1047535433927906,"gpt":0.2617795992806458,"spread":0.1570260558878552,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002724417,0.00006516754,0.00006716625,0.00005678465,0.0001268214,0.00009428074,0.0001292613,0.00003391631,0.000003743528],"category_scores_gemma":[0.00003417555,0.00005575214,0.00001475803,0.00005234684,0.00002940135,0.0003142025,0.00005458206,0.00002039241,0.000001040277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006394247,"about_ca_system_score_gemma":0.00001669381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000472614,"about_ca_topic_score_gemma":0.00004450687,"domain_scores_codex":[0.9994665,0.000005808054,0.00009879767,0.0001745012,0.00008343993,0.0001709349],"domain_scores_gemma":[0.9996218,0.0001147122,0.00003524498,0.0001110324,0.000049757,0.00006747328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003757965,0.0000140623,0.0002396073,0.00004987115,0.000003668389,0.000001800415,0.001006469,0.00001596129,0.0002795539,0.004649526,0.0005065746,0.9932292],"study_design_scores_gemma":[0.001210385,0.0001473526,0.001300382,0.0000570025,0.000007851931,0.00003929054,0.003688757,0.06986652,0.1603407,0.004439218,0.7584831,0.000419442],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003875652,0.001658074,0.9885004,0.001400985,0.00005782922,0.00008322302,2.938516e-7,0.0001307612,0.004292793],"genre_scores_gemma":[0.8256612,0.0008287703,0.16859,0.002384343,0.0002038442,0.00001066965,0.000004957156,0.00001619569,0.002299991],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9928097,"threshold_uncertainty_score":0.2273506,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2489919266","doi":"10.1007/978-981-10-1046-0","title":"Fundamentals of Differential Beamforming","year":2016,"lang":"en","type":"book","venue":"Springer briefs in electrical and computer engineering","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Beamforming; Differential (mechanical device); Microphone; Computer science; Microphone array; Acoustics; Engineering; Telecommunications; Physics; Aerospace engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.00485740277940988,"gpt":0.1859106297270694,"spread":0.1810532269476595,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001103177,0.0003321372,0.0005279739,0.0003973061,0.00003516702,0.0001092238,0.0006023255,0.0001975076,0.000006905652],"category_scores_gemma":[0.00001001535,0.0002896057,0.0001059088,0.0002011006,0.00003256282,0.000236693,0.0004938729,0.0003849213,0.000004434714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000141237,"about_ca_system_score_gemma":0.0001027875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002734444,"about_ca_topic_score_gemma":5.171764e-7,"domain_scores_codex":[0.9982334,0.00001037005,0.0004541592,0.0005235211,0.0002938519,0.0004846379],"domain_scores_gemma":[0.999299,0.0001213173,0.0001399783,0.0002901498,0.00003252905,0.0001169933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001328302,0.00008385294,0.0002999651,0.0005100757,0.0001230449,0.00008857503,0.0001829458,0.0003289976,0.006308767,0.02407417,0.0006100134,0.9673763],"study_design_scores_gemma":[0.006528769,0.001588377,0.009684416,0.01220046,0.0001506031,0.0005774453,0.000001898568,0.5876579,0.1842487,0.03307898,0.1572035,0.007078965],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003343641,0.001487456,0.9916096,0.0000554629,0.0004626974,0.0001458275,0.000002194072,0.000154091,0.002739029],"genre_scores_gemma":[0.3267407,0.002076545,0.5750806,0.0009008207,0.006771239,0.0001171163,0.00002994135,0.0004924129,0.08779062],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9602973,"threshold_uncertainty_score":0.9999556,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127707623","doi":"10.1109/tim.2009.2024697","title":"Temporal Dynamics for Blind Measurement of Room Acoustical Parameters","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Reverberation; Estimator; Speech recognition; Modulation (music); Energy (signal processing); Computer science; Natural sounds; Cepstrum; Noise (video); Artificial intelligence; Pattern recognition (psychology); Acoustics; Mathematics; Physics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04796652431332021,"gpt":0.2738247761681069,"spread":0.2258582518547866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006471646,0.0001372077,0.0001449766,0.0001418239,0.0001850243,0.00009174724,0.000168525,0.00006493395,0.00001104184],"category_scores_gemma":[0.00001807565,0.0001298715,0.00007221744,0.0001538196,0.00005074671,0.0002623018,0.000001611539,0.0001530967,0.000002406332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001238303,"about_ca_system_score_gemma":0.0001459759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001819351,"about_ca_topic_score_gemma":0.0004051148,"domain_scores_codex":[0.998467,0.00002478535,0.0003050345,0.000285517,0.0007289031,0.0001887428],"domain_scores_gemma":[0.9992177,0.00002592305,0.0001117941,0.0002037911,0.0003234749,0.0001173343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000176583,0.0004638594,0.0001559273,0.0001072599,0.0000970763,6.431661e-7,0.0003201118,0.0008354745,0.1857758,0.0004803085,0.00007878004,0.8115081],"study_design_scores_gemma":[0.002715373,0.0003829577,0.0003113659,0.00006793277,0.00006493121,0.000009005004,0.0001859282,0.03795965,0.9570726,0.0007933124,0.00020586,0.0002310895],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07793287,0.000008317779,0.9200753,0.0005871251,0.0008776517,0.0003754171,0.00001081466,0.00004707676,0.00008541807],"genre_scores_gemma":[0.8819333,0.000005829219,0.1178473,0.0001082626,0.00001339163,0.0000695351,0.000001671953,0.000007753883,0.00001294425],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.811277,"threshold_uncertainty_score":0.5296006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115560088","doi":"10.1109/tbme.2006.889191","title":"Acoustic Analysis and Detection of Hypernasality Using a Group Delay Function","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"All India Institute of Speech and Hearing","keywords":"Formant; Speech recognition; Acoustics; Vowel; Measure (data warehouse); Speech processing; Computer science; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.008955212916931557,"gpt":0.2225912738224138,"spread":0.2136360609054823,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003513753,0.0001046052,0.0001574083,0.0005810503,0.0000863216,0.00002891673,0.0001081599,0.00009063361,0.000002772458],"category_scores_gemma":[0.000009453307,0.0001012786,0.0000809346,0.001576397,0.00004052048,0.0002154687,0.000002149186,0.0001636814,8.813792e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005568507,"about_ca_system_score_gemma":0.0000137695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004586615,"about_ca_topic_score_gemma":0.00002511585,"domain_scores_codex":[0.9990672,0.00000983061,0.0002380221,0.000225081,0.0002585724,0.0002013146],"domain_scores_gemma":[0.9995396,0.0000882217,0.00005027017,0.0001534003,0.0000330827,0.00013543],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001543155,0.00006555095,0.0000213762,0.00003438894,0.0001375047,0.000006147518,0.00006357916,0.02880447,0.798527,0.000005292705,1.231795e-7,0.1723191],"study_design_scores_gemma":[0.0002282961,0.0001103128,0.001957061,0.00002751917,0.0001818918,0.00002800576,0.00001337391,0.645236,0.3520385,0.00002116863,0.00002929842,0.0001285982],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2814427,0.00003618365,0.7180475,0.000009124352,0.0002953962,0.00003065315,0.000001282076,0.0001351028,0.000002005298],"genre_scores_gemma":[0.9634915,0.000009282843,0.03643215,0.00002033459,0.00003411054,0.000001797266,3.596027e-7,0.000008406176,0.000002083122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6820487,"threshold_uncertainty_score":0.4130023,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2032556581","doi":"10.1121/1.2108861","title":"Measuring the acoustic effects of compression amplification on speech in noise","year":2006,"lang":"en","type":"article","venue":"The Journal of the Acoustical Society of America","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute on Deafness and Other Communication Disorders","keywords":"QUIET; Acoustics; Noise (video); Background noise; Computer science; Speech recognition; Dynamic range; Physics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01244227588007775,"gpt":0.2360477618239906,"spread":0.2236054859439129,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007872711,0.000112174,0.0002495198,0.00002639309,0.0001674677,0.00002934749,0.001394612,0.00004537249,0.000002013512],"category_scores_gemma":[0.0002716735,0.00004982963,0.0002107269,0.0004930856,0.0003330751,0.0001180404,0.0001931665,0.0004205775,0.000001567064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000599491,"about_ca_system_score_gemma":0.00007404753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005092015,"about_ca_topic_score_gemma":6.740403e-7,"domain_scores_codex":[0.9983742,0.000209887,0.0004422537,0.00009834494,0.000675165,0.0002001043],"domain_scores_gemma":[0.9974407,0.001263811,0.0006893059,0.0004162922,0.0001553584,0.00003452816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007210238,0.0003213159,0.0003728298,0.0001310514,0.00003699585,0.000001969869,0.0007875449,0.0930875,0.8348945,0.00001776995,0.003696063,0.06658036],"study_design_scores_gemma":[0.0009386326,0.0003809257,0.03866832,0.001124322,0.0001562297,0.00006875767,0.0004850458,0.2603556,0.6913586,0.00609124,0.0001825592,0.0001897818],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1617377,0.000420516,0.8332245,0.004092858,0.0002064182,0.0001576258,6.406259e-7,0.00001009447,0.0001496823],"genre_scores_gemma":[0.9584302,0.00008549394,0.04085317,0.0005019992,0.0001048926,8.523414e-7,6.617876e-8,0.000006594996,0.00001667024],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7966926,"threshold_uncertainty_score":0.2591558,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}