{"meta":{"query_hash":"489e066d666b","filters":{"venue":"Conference of the International Speech Communication Association"},"cohort_total":5,"direct_labels_cover":0,"predictions_cover":5,"exported":5,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/489e066d666b","api":"https://metacan.xera.ac/api/v1/cohort?venue=Conference+of+the+International+Speech+Communication+Association"},"results":[{"id":"W120686923","doi":"","title":"Leveraging emotion detection using emotions form yes-no answers","year":2008,"lang":"en","type":"article","venue":"Conference of the International Speech Communication Association","topic":"Emotion and Mood Recognition","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Dialog box; Computer science; Emotion detection; Salient; Generalization; Artificial intelligence; Natural language processing; Support vector machine; Domain (mathematical analysis); Machine learning; Sentiment analysis; Emotion classification; Base (topology); Artificial neural network; Speech recognition; Emotion recognition","score_opus":0.08783353336566915,"score_gpt":0.3199992677605446,"score_spread":0.23216573439487545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W120686923","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92624736,0.000025435209,0.007314298,0.002207288,0.002475772,0.00033959022,0.000022475835,0.00009417023,0.06127361],"genre_scores_gemma":[0.99148893,0.00010369534,0.0013994303,0.00020807459,0.00012653266,0.000019404823,0.00008220726,0.00001724373,0.0065544792],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99820405,0.00032268532,0.0005027862,0.00021496025,0.00057185965,0.0001836535],"domain_scores_gemma":[0.9968992,0.00015816017,0.00093804684,0.0005285944,0.0014333414,0.000042666987],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00067222764,0.00014068148,0.00016137485,0.00018269385,0.0004589009,0.000048161328,0.000671409,0.00018111173,0.0011330218],"category_scores_gemma":[0.0006538746,0.00013508361,0.00017284308,0.0002826204,0.00008733185,0.00038639377,0.00014140779,0.0003306207,0.00019119831],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054034236,0.0038082288,0.39428777,0.00010062816,0.0026807897,0.000007790294,0.042560056,0.001244559,0.27775455,0.036491424,0.021939514,0.21858436],"study_design_scores_gemma":[0.0031572203,0.00012690693,0.89820355,0.00041232523,0.0001920973,0.00018796005,0.0032722498,0.03341221,0.033438,0.011546447,0.015330955,0.0007200583],"about_ca_topic_score_codex":0.0005714542,"about_ca_topic_score_gemma":0.00013805756,"teacher_disagreement_score":0.5039158,"about_ca_system_score_codex":0.0008088899,"about_ca_system_score_gemma":0.00009394977,"threshold_uncertainty_score":0.99978006},"labels":[],"label_agreement":null},{"id":"W2397829000","doi":"","title":"Example-based speech enhancement with joint utilization of spatial, spectral & temporal cues of speech and noise.","year":2012,"lang":"en","type":"article","venue":"Conference of the International Speech Communication Association","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec","funders":"","keywords":"Speech enhancement; Speech recognition; Computer science; Joint (building); Noise (video); Background noise; Voice activity detection; Speech processing; Artificial intelligence; Noise reduction; Engineering; Telecommunications","score_opus":0.05891719383613146,"score_gpt":0.27858942863262653,"score_spread":0.21967223479649506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397829000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84307355,0.0002319648,0.14687932,0.0039898814,0.00029476965,0.0004243923,0.000017546403,0.000042213273,0.0050463905],"genre_scores_gemma":[0.9212549,0.00009231899,0.07833243,0.0000694695,0.000038933107,0.000009232685,0.000035168603,0.000008133508,0.00015945485],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979135,0.00019821951,0.00059336046,0.00018878805,0.00091619114,0.00018997893],"domain_scores_gemma":[0.99632514,0.00021268446,0.0016283966,0.0006551945,0.0011286286,0.000049964303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013143172,0.0001494713,0.00026427026,0.00014394411,0.00009360159,0.000080190155,0.0011606425,0.00008331341,0.000075281474],"category_scores_gemma":[0.000422723,0.00012114513,0.000071795286,0.00028974487,0.00011552202,0.00065875275,0.0003190425,0.00015526633,0.000002463493],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011074611,0.00071250665,0.69275784,0.00012172923,0.00020396555,3.54075e-7,0.0014921702,0.000076599266,0.17878908,0.015295986,0.00030299433,0.11013601],"study_design_scores_gemma":[0.000508886,0.00006870862,0.12657906,0.00023967461,0.000023142942,0.000003347664,0.00007491628,0.0041082315,0.86595577,0.0018852147,0.0004298642,0.00012318566],"about_ca_topic_score_codex":0.0009370779,"about_ca_topic_score_gemma":0.0003861776,"teacher_disagreement_score":0.6871667,"about_ca_system_score_codex":0.00023555188,"about_ca_system_score_gemma":0.00021437995,"threshold_uncertainty_score":0.4940155},"labels":[],"label_agreement":null},{"id":"W2785808055","doi":"","title":"Real-Time Speech Enhancement with GCC-NMF: Demonstration on the Raspberry Pi and NVIDIA Jetson.","year":2017,"lang":"en","type":"article","venue":"Conference of the International Speech Communication Association","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Raspberry pi; Computer science; Pi; Operating system; Speech recognition; Embedded system; Chemistry","score_opus":0.027251940235910006,"score_gpt":0.2662733698507515,"score_spread":0.2390214296148415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785808055","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78532314,0.000051672672,0.0074394085,0.113066755,0.0003745815,0.0005912194,0.000012248992,0.00008323521,0.093057744],"genre_scores_gemma":[0.98123246,0.00028628562,0.015805706,0.00029006784,0.000043485594,0.00002378231,0.000010325189,0.0000075811286,0.0023003165],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983255,0.00016346786,0.00030579837,0.00024293739,0.0008035938,0.00015867164],"domain_scores_gemma":[0.9962633,0.00038406212,0.0013287774,0.0013211129,0.00066571846,0.000037002486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011392208,0.00014282804,0.00014924591,0.000053314176,0.0008044026,0.000860542,0.003085124,0.00008000868,0.000068065914],"category_scores_gemma":[0.0008993757,0.00009350711,0.00005183552,0.000095055286,0.00013462415,0.0007860571,0.0005806268,0.0002371592,0.000031994998],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017225498,0.0007444156,0.0953805,0.000039870978,0.0006228758,0.000003841394,0.002809309,0.00007204329,0.33497477,0.17765953,0.011825211,0.37569538],"study_design_scores_gemma":[0.0010509124,0.00013667633,0.18465148,0.0005955028,0.000045563742,0.000014369242,0.00015498395,0.018276257,0.7649498,0.027073447,0.0026581562,0.00039281923],"about_ca_topic_score_codex":0.00015478386,"about_ca_topic_score_gemma":0.00016219438,"teacher_disagreement_score":0.42997506,"about_ca_system_score_codex":0.00027365488,"about_ca_system_score_gemma":0.00017180295,"threshold_uncertainty_score":0.8298226},"labels":[],"label_agreement":null},{"id":"W2787737401","doi":"","title":"Description of the Homebank Child/Adult Addressee Corpus (HB-CHAAC).","year":2017,"lang":"en","type":"article","venue":"Conference of the International Speech Communication Association","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Natural language processing; Linguistics; Speech recognition; Artificial intelligence; Philosophy","score_opus":0.03006516855866038,"score_gpt":0.2780974164276234,"score_spread":0.24803224786896305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787737401","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46634266,0.0019887262,0.12077653,0.304113,0.0072637694,0.00249715,0.00018984961,0.000705479,0.09612282],"genre_scores_gemma":[0.9768015,0.00013991966,0.021628106,0.00021364624,0.00003260224,0.000014591445,0.000007833902,0.0000064122682,0.0011553831],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983371,0.00017563983,0.00038633283,0.00017146698,0.0008121371,0.00011732148],"domain_scores_gemma":[0.99367183,0.0001316568,0.0023581823,0.0020167162,0.0018017151,0.000019895846],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00074223214,0.00011018485,0.00015407939,0.00006187043,0.00051516254,0.00037289277,0.008344523,0.00011675682,0.000018925348],"category_scores_gemma":[0.0031753709,0.000076958364,0.00012735973,0.00013432413,0.00013745115,0.00091258774,0.0017578369,0.00032365284,0.0000045729385],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026264199,0.00026415556,0.11525785,0.000039948412,0.00016951977,3.5574908e-7,0.0015358615,0.000018957977,0.049371313,0.7641203,0.0036113528,0.06558412],"study_design_scores_gemma":[0.0006896942,0.00003026974,0.34417817,0.0009100925,0.000040407576,0.000011219596,0.000065249005,0.013620164,0.40327698,0.23478274,0.0021035736,0.0002914417],"about_ca_topic_score_codex":0.0005125891,"about_ca_topic_score_gemma":0.00040080884,"teacher_disagreement_score":0.5293375,"about_ca_system_score_codex":0.00031119413,"about_ca_system_score_gemma":0.0001132944,"threshold_uncertainty_score":0.9970208},"labels":[],"label_agreement":null},{"id":"W3022549683","doi":"","title":"SLP-AA: Tools for Sign Language Phonetic and Phonological Research.","year":2019,"lang":"en","type":"article","venue":"Conference of the International Speech Communication Association","topic":"Hearing Impairment and Communication","field":"Psychology","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Natural language processing; Speech recognition; Sign language; Sign (mathematics); Artificial intelligence; Linguistics; Mathematics","score_opus":0.1303975879616909,"score_gpt":0.40042628004438857,"score_spread":0.27002869208269764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022549683","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.945562,0.0001882902,0.00013147561,0.0127312755,0.0003680318,0.00069189403,0.000021184032,0.00003484544,0.040271007],"genre_scores_gemma":[0.98817974,0.000107262305,0.0010955648,0.00015416222,0.000033197684,0.000102202364,0.000060133647,0.000009244524,0.010258485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99845326,0.00050039374,0.00029976098,0.00016762313,0.00040602149,0.00017294945],"domain_scores_gemma":[0.99644816,0.0017454356,0.00034326263,0.0007975139,0.00063841045,0.00002722166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021114289,0.00008020568,0.00013696653,0.00008408546,0.00013949817,0.00013010313,0.0012084706,0.00014312056,0.00067118416],"category_scores_gemma":[0.0015856159,0.00006791216,0.00006469729,0.00014216964,0.00007978828,0.000196563,0.00039966364,0.00031578608,0.00012544033],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044746642,0.0010667801,0.21406984,0.000053066247,0.00056438247,3.8994338e-7,0.01963658,0.000020563346,0.09781053,0.36217576,0.023016615,0.28113803],"study_design_scores_gemma":[0.0025261207,0.00026567103,0.9037423,0.00020523164,0.000041306364,0.0000056032945,0.0074168867,0.0026811622,0.010265991,0.024162253,0.048384536,0.0003029407],"about_ca_topic_score_codex":0.00023167014,"about_ca_topic_score_gemma":0.00007269446,"teacher_disagreement_score":0.68967247,"about_ca_system_score_codex":0.00026336833,"about_ca_system_score_gemma":0.000057602258,"threshold_uncertainty_score":0.7348996},"labels":[],"label_agreement":null}]}