{"meta":{"query_hash":"0c76d1bcefc8","filters":{"venue":"Computer Speech & Language"},"cohort_total":21,"direct_labels_cover":0,"predictions_cover":21,"exported":21,"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/0c76d1bcefc8","api":"https://metacan.xera.ac/api/v1/cohort?venue=Computer+Speech+%26+Language"},"results":[{"id":"W1972278020","doi":"10.1006/csla.2000.0143","title":"Tree-structured vector quantization for speech recognition","year":2000,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Smoothing; Hidden Markov model; Computer science; Vector quantization; Pattern recognition (psychology); Speech recognition; Gaussian; Tree (set theory); Entropy (arrow of time); Artificial intelligence; Feature vector; Mixture model; Curse of dimensionality; Mathematics","score_opus":0.019873500248218698,"score_gpt":0.2541196303712127,"score_spread":0.234246130122994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972278020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043886728,0.0019612678,0.98891836,0.00022964722,0.00028201388,0.00005080829,0.00068634516,0.002240837,0.0012419645],"genre_scores_gemma":[0.15709428,0.0023374767,0.8267862,0.00033130028,0.00026411976,0.00029257746,0.0038958986,0.00028378953,0.0087143155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993616,0.00016133173,0.000076097625,0.000117040145,0.00022258198,0.000061340645],"domain_scores_gemma":[0.9991405,0.0002772054,0.000045041354,0.00019456037,0.00032085137,0.000021812235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061191915,0.0006180851,0.0010408241,0.000634757,0.00041668274,0.0008671399,0.0010243284,0.0008200989,0.007481222],"category_scores_gemma":[0.0021795845,0.00028629808,0.000464,0.0019035772,0.0004436638,0.0013994616,0.0005682086,0.0011171747,0.0029135593],"study_design_candidate":"simulation_or_modeling","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":[0.0002138356,0.00007949204,0.00019111024,0.00017568498,0.000032776654,0.000037741167,0.000058780683,0.040383775,0.015856097,0.049676728,0.028595285,0.8646987],"study_design_scores_gemma":[0.0000625044,0.0001190756,0.00043452656,0.00005619404,0.000023122946,0.00008430851,0.000047316244,0.8943922,0.012811526,0.07708989,0.014840768,0.000038600498],"about_ca_topic_score_codex":0.009400433,"about_ca_topic_score_gemma":0.010892937,"teacher_disagreement_score":0.009400433,"about_ca_system_score_codex":0.0006722113,"about_ca_system_score_gemma":0.0014197979,"threshold_uncertainty_score":0.025027156},"labels":[],"label_agreement":null},{"id":"W1995193848","doi":"10.1016/j.csl.2012.11.001","title":"Adjusting dysarthric speech signals to be more intelligible","year":2012,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":54,"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 Toronto","funders":"","keywords":"Computer science; Speech recognition; Artificial intelligence","score_opus":0.053916686106043304,"score_gpt":0.3787507243040557,"score_spread":0.3248340381980124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995193848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9696521,0.00017071888,0.02442559,0.00026634106,0.00019801773,0.00011065253,0.00023574264,0.00070424465,0.0042365524],"genre_scores_gemma":[0.9840634,0.00013766394,0.01253392,0.00026494227,0.000039186205,0.00006105841,0.00018671175,0.0002567123,0.0024564248],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99979097,0.00003077592,0.000029668408,0.0000893988,0.00003563154,0.000023564624],"domain_scores_gemma":[0.9994068,0.0002590269,0.00007965297,0.00007665976,0.00012487605,0.000052983614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002987048,0.00042617598,0.00018049535,0.00023199101,0.00013085238,0.0007216309,0.00027274166,0.0005138786,0.006293369],"category_scores_gemma":[0.003688403,0.00014830157,0.00016117592,0.00012831957,0.00014639973,0.00039375405,0.00034458635,0.00037651634,0.0015276602],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007738983,0.00015836934,0.0019563138,0.000105943865,0.00004271666,0.00007189971,0.00018678968,0.0008824065,0.9602126,0.00034186512,0.00031657546,0.034950715],"study_design_scores_gemma":[0.0010705634,0.0037922931,0.1496,0.00010653544,0.0006324799,0.001297587,0.0010899868,0.024277214,0.7995072,0.0036561503,0.014799758,0.00017017496],"about_ca_topic_score_codex":0.0004234962,"about_ca_topic_score_gemma":0.00040237073,"teacher_disagreement_score":0.006293369,"about_ca_system_score_codex":0.00012189112,"about_ca_system_score_gemma":0.0001429996,"threshold_uncertainty_score":0.021053374},"labels":[],"label_agreement":null},{"id":"W2036126214","doi":"10.1016/j.csl.2014.10.007","title":"Hybrid Arabic–French machine translation using syntactic re-ordering and morphological pre-processing","year":2014,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine translation; Natural language processing; Artificial intelligence; Example-based machine translation; Arabic; BLEU; Translation (biology); Verb; Linguistics","score_opus":0.016871099164201,"score_gpt":0.2750535633622381,"score_spread":0.2581824641980371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036126214","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08576951,0.0021109465,0.8244672,0.0011028722,0.0020487143,0.00054500985,0.0050079473,0.045092456,0.03385535],"genre_scores_gemma":[0.25203997,0.0008393508,0.71475995,0.0004747667,0.0004178812,0.00025660484,0.0097660925,0.004262144,0.017183226],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990181,0.00028538163,0.000115922136,0.00027023794,0.00019027328,0.00012015111],"domain_scores_gemma":[0.9982003,0.00043876847,0.00008760811,0.00033465074,0.0008772926,0.00006133596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007085794,0.00222655,0.0013697473,0.0021915743,0.0013276329,0.0029536013,0.0008846805,0.0011389783,0.016757041],"category_scores_gemma":[0.0020843113,0.00059973187,0.0013625467,0.0017032138,0.00043808296,0.0014157034,0.0014758903,0.0013098177,0.01426248],"study_design_candidate":"simulation_or_modeling","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":[0.0010801351,0.00034957653,0.0016187918,0.0013590122,0.00035554508,0.0028748347,0.0009090123,0.0108733,0.18602452,0.012821395,0.042896304,0.73883754],"study_design_scores_gemma":[0.0004673254,0.0010935676,0.006548847,0.00034660118,0.0010104023,0.004979133,0.0019689926,0.3327609,0.38330317,0.025200082,0.24184254,0.0004784725],"about_ca_topic_score_codex":0.004816342,"about_ca_topic_score_gemma":0.0077116815,"teacher_disagreement_score":0.016757041,"about_ca_system_score_codex":0.0005694743,"about_ca_system_score_gemma":0.0016667655,"threshold_uncertainty_score":0.05605787},"labels":[],"label_agreement":null},{"id":"W2058080055","doi":"10.1016/j.csl.2014.06.002","title":"Unsupervised language model adaptation using LDA-based mixture models and latent semantic marginals","year":2014,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Artificial intelligence; Language model; Topic model; Probabilistic latent semantic analysis; Pattern recognition (psychology); Scaling; Mixture model; Cluster analysis; Machine learning; Mathematics","score_opus":0.03687698171248772,"score_gpt":0.25634630427735217,"score_spread":0.21946932256486446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058080055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006576063,0.0002061521,0.9914766,0.00008261784,0.000061834595,0.000028249422,0.000091083,0.0010422092,0.00043508294],"genre_scores_gemma":[0.37648252,0.0008077711,0.61003554,0.00027312475,0.00025161286,0.00045055742,0.0025079057,0.0017552123,0.007435794],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985519,0.0006498906,0.000070834525,0.00036112932,0.0002453713,0.000120919976],"domain_scores_gemma":[0.9982084,0.00095000985,0.00008027991,0.00030821576,0.00038246406,0.00007055859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00184013,0.0011116486,0.001268594,0.0011641285,0.00074379885,0.0012551544,0.0015421639,0.00101357,0.0024138256],"category_scores_gemma":[0.004931001,0.0010689262,0.0028795665,0.0012108248,0.0007716623,0.0019322571,0.0021239857,0.0027451026,0.0033646324],"study_design_candidate":"simulation_or_modeling","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":[0.0009079603,0.00038199857,0.0022620293,0.00023250288,0.00062801555,0.00019690079,0.0005612398,0.35975546,0.035798423,0.01854072,0.007999299,0.5727355],"study_design_scores_gemma":[0.000012616023,0.000018796403,0.00036956408,0.0000080785985,0.000031670916,0.000042911764,0.000021893033,0.99102026,0.0026775834,0.0047799316,0.0009929822,0.000023675693],"about_ca_topic_score_codex":0.005633029,"about_ca_topic_score_gemma":0.008635009,"teacher_disagreement_score":0.005633029,"about_ca_system_score_codex":0.000533251,"about_ca_system_score_gemma":0.0010558747,"threshold_uncertainty_score":0.011200488},"labels":[],"label_agreement":null},{"id":"W2059790057","doi":"10.1016/j.csl.2014.11.003","title":"Native and non-native class discrimination using speech rhythm- and auditory-based cues","year":2014,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; University of New Brunswick; Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speech recognition; Support vector machine; Metric (unit); Mixture model; Rhythm; Context (archaeology); Artificial intelligence; Pattern recognition (psychology)","score_opus":0.011635727441856787,"score_gpt":0.261708059154234,"score_spread":0.2500723317123772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059790057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865877,0.00014390882,0.0061737862,0.00004581263,0.00011682043,0.00003586614,0.00012430763,0.00016605812,0.006605808],"genre_scores_gemma":[0.99447614,0.00010754039,0.0027994749,0.00009332637,0.000030160718,0.000022259106,0.0002457559,0.00007369021,0.0021517205],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9995921,0.00007482129,0.000026775466,0.00013063173,0.000072565635,0.00010302617],"domain_scores_gemma":[0.9977373,0.0013729853,0.000058264737,0.00012502664,0.0003310828,0.00037527227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010680956,0.0003811947,0.00047737037,0.0005633928,0.00030945716,0.0012227853,0.00033425787,0.0007525661,0.006025706],"category_scores_gemma":[0.0042779343,0.00020934107,0.00025543032,0.00017376436,0.00032522957,0.0013728988,0.0008943677,0.00054907554,0.0014566109],"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":[0.009961925,0.0003957085,0.013438715,0.00022926171,0.00005406861,0.00028955762,0.0012857249,0.00040114427,0.8916619,0.00051052426,0.00066951616,0.081101894],"study_design_scores_gemma":[0.00084062765,0.0050072884,0.53574204,0.00019883238,0.0005247899,0.0041329325,0.0061883973,0.047893956,0.38704062,0.004804527,0.007295014,0.00033092417],"about_ca_topic_score_codex":0.001253566,"about_ca_topic_score_gemma":0.0026116837,"teacher_disagreement_score":0.006025706,"about_ca_system_score_codex":0.00012017325,"about_ca_system_score_gemma":0.00035925236,"threshold_uncertainty_score":0.020157993},"labels":[],"label_agreement":null},{"id":"W2083400649","doi":"10.1016/j.csl.2013.04.009","title":"Prior and contextual emotion of words in sentential context","year":2013,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":47,"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 Ottawa","funders":"","keywords":"Computer science; Sentence; Context (archaeology); Natural language processing; Set (abstract data type); Word (group theory); Feature (linguistics); Focus (optics); Task (project management); Similarity (geometry); Artificial intelligence; Contrast (vision); Affect (linguistics); Function (biology); Linguistics; Image (mathematics)","score_opus":0.009483769740171108,"score_gpt":0.23875473576759712,"score_spread":0.22927096602742603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083400649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.853341,0.001757172,0.10293531,0.0009336685,0.0005216326,0.000115208764,0.0010542183,0.0003412377,0.039000608],"genre_scores_gemma":[0.99132884,0.00024965196,0.0055492613,0.000043331984,0.00020118477,0.000029246135,0.00035880986,0.000042462027,0.0021971816],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99922776,0.00019363956,0.000065921064,0.00021536004,0.00019015482,0.000107263644],"domain_scores_gemma":[0.997414,0.001171502,0.00027698543,0.00024067641,0.00066813955,0.00022862971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084911095,0.0003607833,0.0003353706,0.0012311555,0.00067325594,0.0019929325,0.00024249095,0.00053102,0.004652762],"category_scores_gemma":[0.005569848,0.00021435998,0.00040145635,0.0008382377,0.00087323954,0.0036504152,0.000900348,0.0011407422,0.0010658823],"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":[0.005349018,0.000853456,0.087586276,0.001084805,0.0004102737,0.0026456832,0.015608605,0.009958797,0.35453516,0.12613551,0.009407692,0.38642478],"study_design_scores_gemma":[0.00014268397,0.0021461819,0.51764715,0.00058059784,0.001089214,0.0032693702,0.013281182,0.19551374,0.06768957,0.14046308,0.057802584,0.00037465236],"about_ca_topic_score_codex":0.0014132371,"about_ca_topic_score_gemma":0.0023532226,"teacher_disagreement_score":0.004652762,"about_ca_system_score_codex":0.0005835679,"about_ca_system_score_gemma":0.00032841924,"threshold_uncertainty_score":0.015565038},"labels":[],"label_agreement":null},{"id":"W2114705006","doi":"10.1016/j.csl.2009.02.004","title":"Syllabification rules versus data-driven methods in a language with low syllabic complexity: The case of Italian","year":2009,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Phonetics and Phonology Research","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Syllabification; Syllabic verse; Computer science; Syllable; Natural language processing; Artificial intelligence; Lexicon; Parsing; Machine translation; Speech recognition","score_opus":0.08642458988048203,"score_gpt":0.441595487778507,"score_spread":0.355170897898025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114705006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62381965,0.0008735554,0.3544412,0.0020289011,0.00006557191,0.00011138947,0.00020901086,0.0009303233,0.017520297],"genre_scores_gemma":[0.88662875,0.00015740519,0.11168275,0.00008822056,0.000024617662,0.000032784585,0.00008919597,0.0001497954,0.0011465786],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99807775,0.0011809262,0.00009493326,0.00021063954,0.00031463898,0.000121153724],"domain_scores_gemma":[0.9877885,0.0098729525,0.00035973685,0.0011723416,0.000653643,0.00015288808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040914607,0.0002859928,0.00040467313,0.000679105,0.0007096021,0.002689282,0.0009337875,0.0010428742,0.0013467156],"category_scores_gemma":[0.015632661,0.00034299723,0.0004460759,0.00091063423,0.0015457916,0.0019179775,0.0008614316,0.0009566552,0.0003259034],"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":[0.0014005376,0.00042658966,0.045648623,0.00059088034,0.00021574386,0.00400085,0.0072862566,0.14591502,0.03073296,0.22754957,0.0037668368,0.53246605],"study_design_scores_gemma":[0.000116936186,0.00009304704,0.009588452,0.000057797584,0.000098289536,0.0007622849,0.0011063988,0.88010454,0.013761117,0.08759505,0.00663122,0.00008487823],"about_ca_topic_score_codex":0.014735299,"about_ca_topic_score_gemma":0.015771188,"teacher_disagreement_score":0.014735299,"about_ca_system_score_codex":0.00092515664,"about_ca_system_score_gemma":0.0014271092,"threshold_uncertainty_score":0.02929908},"labels":[],"label_agreement":null},{"id":"W2148812765","doi":"10.1006/csla.1999.0136","title":"A path-stack algorithm for optimizing dynamic regimes in a statistical hidden dynamic model of speech","year":2000,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"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 Waterloo","funders":"","keywords":"Computer science; Hidden Markov model; Utterance; Speech recognition; Stack (abstract data type); Path (computing); Phone; Reduction (mathematics); Set (abstract data type); Segmentation; Algorithm; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.013258436234086577,"score_gpt":0.2679317228246664,"score_spread":0.2546732865905798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148812765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005868726,0.0001124156,0.99234915,0.00006651079,0.000018447905,0.00005023884,0.000045892906,0.0008689514,0.00061959354],"genre_scores_gemma":[0.124701545,0.00019685595,0.871011,0.000100643476,0.000036357815,0.00042443405,0.0003638718,0.00058310817,0.0025821282],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963784,0.00012241486,0.000022537484,0.00009269724,0.00007798621,0.00004657844],"domain_scores_gemma":[0.9989518,0.00078838965,0.00004380521,0.000057349156,0.0001164475,0.000042194486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001977727,0.0016751288,0.0016877683,0.0012574274,0.0010481616,0.00094597635,0.0018026943,0.0025240844,0.006168039],"category_scores_gemma":[0.0042053037,0.0018574471,0.0013140804,0.0012191166,0.001102629,0.0021296893,0.0019004245,0.0023988388,0.0011336115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014223286,0.00007141579,0.00036173832,0.000050805844,0.000074924654,0.0000523985,0.0000738671,0.83392304,0.0016104189,0.013500993,0.0015830412,0.1485551],"study_design_scores_gemma":[0.000011601376,0.000013844581,0.000023926652,0.0000032619553,0.000006643299,0.0000042506,0.0000040890136,0.99614775,0.00022348286,0.0033316254,0.00022501474,0.00000455433],"about_ca_topic_score_codex":0.017531916,"about_ca_topic_score_gemma":0.017948803,"teacher_disagreement_score":0.017531916,"about_ca_system_score_codex":0.0011641075,"about_ca_system_score_gemma":0.0030905043,"threshold_uncertainty_score":0.034859776},"labels":[],"label_agreement":null},{"id":"W2189903590","doi":"10.1016/j.csl.2015.11.002","title":"Speech Production in Speech Technologies: Introduction to the CSL Special Issue","year":2015,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","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":"Toronto Rehabilitation Institute","funders":"","keywords":"Computer science; Speech production; Speech technology; Production (economics); Context (archaeology); Speech processing; Speech recognition; History","score_opus":0.01931376996621591,"score_gpt":0.2584920550608656,"score_spread":0.23917828509464967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189903590","genre_codex":"review","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003580717,0.5749885,0.13398972,0.054377142,0.10541261,0.00029943683,0.0011892621,0.003140173,0.123022415],"genre_scores_gemma":[0.033947907,0.39838818,0.05692056,0.013795653,0.2316523,0.00044122405,0.0026228162,0.0028008649,0.25943056],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984059,0.00028552432,0.00027358497,0.0003166947,0.00061448215,0.00010374749],"domain_scores_gemma":[0.99400663,0.0018912634,0.00021200516,0.0004778018,0.00295244,0.00045983042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003893252,0.0012313905,0.0011623024,0.0058639958,0.0010304379,0.005729657,0.0017031465,0.0032483265,0.020887103],"category_scores_gemma":[0.004534401,0.00083529047,0.0007980186,0.0031044674,0.0024708644,0.0050787213,0.0029973781,0.0041748667,0.017898617],"study_design_candidate":"not_applicable","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":[0.00007923703,0.0001412045,0.00045837773,0.0010200448,0.000021248581,0.00014121163,0.00020391587,0.0006781704,0.005261942,0.012479598,0.26757464,0.71194047],"study_design_scores_gemma":[0.000005613782,0.00008914422,0.0015819956,0.0005035844,0.000012622497,0.0005861665,0.00011698146,0.0013131818,0.0022364333,0.0054299114,0.9880824,0.000041991007],"about_ca_topic_score_codex":0.0035184915,"about_ca_topic_score_gemma":0.0056056674,"teacher_disagreement_score":0.020887103,"about_ca_system_score_codex":0.002318445,"about_ca_system_score_gemma":0.002382567,"threshold_uncertainty_score":0.069874346},"labels":[],"label_agreement":null},{"id":"W2597891111","doi":"10.1016/j.csl.2017.01.014","title":"On integrating a language model into neural machine translation","year":2017,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Machine translation; Computer science; Artificial intelligence; Phrase; Natural language processing; Translation (biology); BLEU; Language model; Baseline (sea); Example-based machine translation; Turkish; Machine learning; Linguistics","score_opus":0.016226769020705842,"score_gpt":0.3056925943937503,"score_spread":0.28946582537304444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2597891111","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020721592,0.0010915786,0.96647817,0.0013703201,0.00043977302,0.00008953134,0.0002617546,0.0043876595,0.005159703],"genre_scores_gemma":[0.377238,0.0014543721,0.6033342,0.0012697992,0.0004483782,0.0002052399,0.0012449445,0.0009349189,0.0138701415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993325,0.0002662366,0.000049176168,0.00015893349,0.00013199869,0.00006114613],"domain_scores_gemma":[0.9979431,0.0012639241,0.000075134754,0.0002777515,0.00038197133,0.000058021113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001580626,0.00082933984,0.0010506365,0.00081567524,0.00076676905,0.0016548432,0.0013946102,0.0017792145,0.0055995784],"category_scores_gemma":[0.005474296,0.0005853667,0.0010060229,0.0013013337,0.00057609647,0.0041709435,0.0016307187,0.001774339,0.002749508],"study_design_candidate":"simulation_or_modeling","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":[0.00047349668,0.00029155987,0.0013964843,0.0002555763,0.00025598417,0.00028977345,0.00019285346,0.27546114,0.013171976,0.044536762,0.012009058,0.65166533],"study_design_scores_gemma":[0.000021138456,0.000048939266,0.00013997214,0.00001506933,0.00004655597,0.000050420924,0.000023762932,0.95952785,0.0027212726,0.035426244,0.0019645747,0.00001416443],"about_ca_topic_score_codex":0.007235065,"about_ca_topic_score_gemma":0.011840444,"teacher_disagreement_score":0.007235065,"about_ca_system_score_codex":0.00061969395,"about_ca_system_score_gemma":0.0010959979,"threshold_uncertainty_score":0.018732488},"labels":[],"label_agreement":null},{"id":"W2766171655","doi":"10.1016/j.csl.2017.10.006","title":"Application of the pairwise variability index of speech rhythm with particle swarm optimization to the classification of native and non-native accents","year":2017,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Université de Moncton; Université du Québec à Trois-Rivières","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Particle swarm optimization; Support vector machine; Pairwise comparison; Metric (unit); Artificial intelligence; Speech recognition; Pattern recognition (psychology); Rhythm; Generalization; Point (geometry); Machine learning; Mathematics","score_opus":0.015791004986658013,"score_gpt":0.2634387689169221,"score_spread":0.24764776393026408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766171655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40081227,0.0007923974,0.59566283,0.00025930087,0.00016362825,0.00007783033,0.00014174882,0.0004096035,0.001680389],"genre_scores_gemma":[0.91662306,0.00015372445,0.082379654,0.000023512237,0.000044015796,0.000040970383,0.00022301941,0.000043332155,0.00046862592],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969757,0.00010522258,0.00002821083,0.00008242664,0.00005756788,0.000029033868],"domain_scores_gemma":[0.9990158,0.00061037595,0.00006825929,0.000060065882,0.00020170434,0.000043693486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017238517,0.00062481617,0.00080958614,0.0011159866,0.00041405458,0.0008804871,0.0004178982,0.0004676128,0.00029575033],"category_scores_gemma":[0.002992883,0.00019355041,0.0007731203,0.00083821977,0.00035136408,0.00039212624,0.00045793928,0.0005719063,0.000084740626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047380474,0.00023590194,0.015821438,0.00012129141,0.0003804475,0.00012147233,0.00029189026,0.6489842,0.014600356,0.00203548,0.001578162,0.3153557],"study_design_scores_gemma":[0.0000047586636,0.000031546588,0.0024392433,0.0000025017084,0.000013320215,0.0000107973,0.000021831082,0.9964587,0.00064282224,0.00029425792,0.00007498237,0.000005224724],"about_ca_topic_score_codex":0.0050573344,"about_ca_topic_score_gemma":0.0026748371,"teacher_disagreement_score":0.0050573344,"about_ca_system_score_codex":0.0003474864,"about_ca_system_score_gemma":0.00062438485,"threshold_uncertainty_score":0.01005578},"labels":[],"label_agreement":null},{"id":"W3136363192","doi":"10.1016/j.csl.2022.101429","title":"On the effect of dropping layers of pre-trained transformer models","year":2022,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Topic Modeling","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Transformer; Computer science; Limiting; Sentence; Artificial intelligence; Paraphrase; Machine learning; Natural language processing; Engineering","score_opus":0.010209370206985395,"score_gpt":0.2361752071494904,"score_spread":0.225965836942505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136363192","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55225635,0.010741075,0.38277832,0.004456219,0.0038667629,0.00035228164,0.0022250758,0.01836221,0.024961716],"genre_scores_gemma":[0.88128775,0.0015847647,0.09477663,0.0016504881,0.00023467094,0.000078275916,0.0027757536,0.002203322,0.015408248],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835545,0.00054733304,0.00010605688,0.00037824063,0.00026848505,0.000344414],"domain_scores_gemma":[0.9882004,0.008810316,0.00022343658,0.0012505098,0.0011667116,0.0003485485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040103067,0.0025430154,0.0012483858,0.0006874642,0.00091651717,0.0023163348,0.0016003912,0.0029419817,0.011600522],"category_scores_gemma":[0.028775083,0.0008883465,0.0008605853,0.0007098003,0.00096132193,0.004007506,0.0017392121,0.004294732,0.0024016693],"study_design_candidate":"simulation_or_modeling","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":[0.009604643,0.0012805853,0.0073509645,0.00089980476,0.001031077,0.00079444004,0.00053044397,0.35849378,0.09318565,0.006643346,0.027110022,0.49307522],"study_design_scores_gemma":[0.0002535243,0.0006951978,0.0039884024,0.00016890018,0.00064573524,0.00025240157,0.0003313408,0.92283076,0.06118226,0.0044418103,0.005149716,0.000060039536],"about_ca_topic_score_codex":0.032517157,"about_ca_topic_score_gemma":0.06206566,"teacher_disagreement_score":0.032517157,"about_ca_system_score_codex":0.0011184601,"about_ca_system_score_gemma":0.002189918,"threshold_uncertainty_score":0.06465578},"labels":[],"label_agreement":null},{"id":"W3214734602","doi":"10.1016/j.csl.2021.101322","title":"Empirical Mode Decomposition articulation feature extraction on Parkinson’s Diadochokinesia","year":2021,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"H2020 Marie Skłodowska-Curie Actions; Horizon 2020; Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme; Universidad de Antioquia","keywords":"Segmentation; Computer science; Artificial intelligence; Pattern recognition (psychology); Hilbert–Huang transform; Frame (networking); Feature (linguistics); Filter (signal processing); Speech recognition; Computer vision; Telecommunications","score_opus":0.015105509905435072,"score_gpt":0.377200725557779,"score_spread":0.3620952156523439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214734602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77330047,0.0035111923,0.21835527,0.00028195805,0.00018387745,0.00007470984,0.0011608684,0.00054901215,0.0025826346],"genre_scores_gemma":[0.9675033,0.00089566835,0.028380716,0.00003332272,0.000051952822,0.000021474403,0.0007709129,0.000042767802,0.0022998499],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9999182,0.000014571611,0.000009834544,0.000017350338,0.00002462389,0.000015253291],"domain_scores_gemma":[0.9998529,0.00005466142,0.000012990063,0.000010647066,0.000055842367,0.0000129345335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018459753,0.0003677827,0.00031854754,0.00085797877,0.00016844239,0.0002641182,0.000107350075,0.00024976252,0.0011015177],"category_scores_gemma":[0.00044057687,0.000085231986,0.00042126098,0.00050853397,0.00007794116,0.00015201535,0.00021896804,0.00023247948,0.00046462208],"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":[0.0012874958,0.00008714752,0.019756533,0.00025305853,0.00008541329,0.0013934604,0.00015002584,0.007960692,0.22633928,0.00048300528,0.0020080875,0.7401958],"study_design_scores_gemma":[0.000089618836,0.0006356954,0.37870276,0.00011977682,0.0003914061,0.0047593275,0.00057779194,0.51314986,0.09150145,0.0011438661,0.008843679,0.000084800056],"about_ca_topic_score_codex":0.0025904002,"about_ca_topic_score_gemma":0.0027932327,"teacher_disagreement_score":0.0025904002,"about_ca_system_score_codex":0.000094766845,"about_ca_system_score_gemma":0.00018248263,"threshold_uncertainty_score":0.005150676},"labels":[],"label_agreement":null},{"id":"W4384936706","doi":"10.1016/j.csl.2023.101538","title":"Trends and developments in automatic speech recognition research","year":2023,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Computer science; Discriminative model; Exploit; Variety (cybernetics); Artificial intelligence; Speech recognition; Natural language; Deep learning; SIGNAL (programming language); Machine learning; Natural language processing","score_opus":0.07391361334822268,"score_gpt":0.34104259928551184,"score_spread":0.2671289859372892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384936706","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029608384,0.81075585,0.06329128,0.025257993,0.0035699662,0.00012912962,0.000891842,0.001140388,0.065355174],"genre_scores_gemma":[0.14576894,0.6880602,0.11064969,0.0061450773,0.009207552,0.00014714901,0.0022319953,0.00031903552,0.03747039],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99788755,0.00042935938,0.00023422696,0.0004890285,0.0008165288,0.00014335455],"domain_scores_gemma":[0.98454237,0.007720276,0.0008892201,0.00047372322,0.005798618,0.00057583227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004845304,0.0005369485,0.00079680583,0.0038431387,0.00043949258,0.0033932147,0.001265455,0.0016786068,0.012778999],"category_scores_gemma":[0.0067300173,0.00037722522,0.00055254815,0.0046215155,0.0013303922,0.0044539496,0.0006883715,0.0017227468,0.006671648],"study_design_candidate":"not_applicable","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":[0.00023415458,0.0001735318,0.0039294576,0.0023387102,0.000028402541,0.00006843449,0.00021801911,0.00077521557,0.0144280605,0.019140296,0.0121985935,0.9464672],"study_design_scores_gemma":[0.000044306824,0.0006987044,0.01829924,0.0022671253,0.00015314037,0.0015550549,0.0014615315,0.014171195,0.021457436,0.024239706,0.91552866,0.0001239692],"about_ca_topic_score_codex":0.0018734264,"about_ca_topic_score_gemma":0.002196464,"teacher_disagreement_score":0.012778999,"about_ca_system_score_codex":0.0011239782,"about_ca_system_score_gemma":0.002335317,"threshold_uncertainty_score":0.04275},"labels":[],"label_agreement":null},{"id":"W4391421598","doi":"10.1016/j.csl.2024.101685","title":"Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge","year":2024,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"Agence Nationale de la Recherche; University of Sheffield","keywords":"Computer science; Speech recognition; Speech enhancement; Leverage (statistics); Task (project management); Noise (video); Distortion (music); Artificial intelligence; Domain adaptation; Noise reduction","score_opus":0.023781224384059923,"score_gpt":0.3505703286582682,"score_spread":0.32678910427420826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391421598","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9044301,0.0053551244,0.06439551,0.0004375333,0.001210332,0.0011348594,0.0048628263,0.0042160177,0.013957605],"genre_scores_gemma":[0.9033087,0.0010557176,0.05610544,0.0005338486,0.000497852,0.00091300247,0.019746734,0.00092514144,0.016913561],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9949273,0.0019746854,0.0004310638,0.0009687413,0.0014160934,0.00028218498],"domain_scores_gemma":[0.99241877,0.0032448503,0.00045411414,0.00074990775,0.0023994918,0.00073296874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004862581,0.0018713963,0.0011261549,0.00083696237,0.0005405745,0.0013769778,0.00074382266,0.0013064818,0.0023083834],"category_scores_gemma":[0.010962545,0.00023729658,0.0005249565,0.00030640545,0.0007710581,0.00088982814,0.0019312322,0.00090588833,0.0020173572],"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":[0.010428786,0.002851246,0.021248931,0.0065689017,0.0015539005,0.0015742555,0.0030255858,0.04655745,0.39539534,0.00078609964,0.052727353,0.4572823],"study_design_scores_gemma":[0.0014813837,0.018434254,0.2931702,0.00082209543,0.0014081527,0.005245409,0.005423777,0.24902225,0.34534052,0.0020920166,0.0765193,0.0010406914],"about_ca_topic_score_codex":0.0014042953,"about_ca_topic_score_gemma":0.0032373369,"teacher_disagreement_score":0.004862581,"about_ca_system_score_codex":0.00034432922,"about_ca_system_score_gemma":0.0004955782,"threshold_uncertainty_score":0.025716066},"labels":[],"label_agreement":null},{"id":"W4401281176","doi":"10.1016/j.csl.2024.101695","title":"Speech self-supervised representations benchmarking: A case for larger probing heads","year":2024,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Mila - Quebec Artificial Intelligence Institute","funders":"Agence de l'innovation de Défense","keywords":"Benchmarking; Computer science; Ranking (information retrieval); Inference; Task (project management); Downstream (manufacturing); Generalization; Feature (linguistics); Set (abstract data type); Artificial intelligence; Architecture; Machine learning; Benchmark (surveying); Data set; Natural language processing","score_opus":0.02313783000429004,"score_gpt":0.2944255563429296,"score_spread":0.27128772633863957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401281176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28022808,0.0017372124,0.6750554,0.0030275262,0.0008945772,0.00056667026,0.0023794996,0.020586703,0.015524325],"genre_scores_gemma":[0.8184054,0.00016002155,0.16932388,0.00094455096,0.00013987883,0.00032672333,0.0040117335,0.0022525375,0.0044352217],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98765045,0.0060689505,0.0006856744,0.0023268335,0.002479623,0.00078838604],"domain_scores_gemma":[0.9627472,0.017892353,0.0007019229,0.012053394,0.0056910906,0.0009140311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014434551,0.0010577983,0.0018579422,0.0008149768,0.0012735862,0.0025173812,0.00396877,0.0032402987,0.010965627],"category_scores_gemma":[0.062120564,0.0004530371,0.00068642455,0.0012091451,0.0018207714,0.0050551924,0.0047403225,0.0025604141,0.002778806],"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":[0.0027788756,0.0010286814,0.012374251,0.0007342944,0.0003583696,0.0007450592,0.0014298514,0.11561867,0.046311706,0.016393734,0.030144945,0.7720816],"study_design_scores_gemma":[0.0002108743,0.0016536199,0.011882713,0.000217963,0.00018078592,0.0012409892,0.0019646664,0.8060158,0.087267615,0.046566244,0.042618815,0.00017983293],"about_ca_topic_score_codex":0.004018226,"about_ca_topic_score_gemma":0.006908358,"teacher_disagreement_score":0.014434551,"about_ca_system_score_codex":0.0010609829,"about_ca_system_score_gemma":0.0017797574,"threshold_uncertainty_score":0.07633811},"labels":[],"label_agreement":null},{"id":"W4402127086","doi":"10.1016/j.csl.2024.101715","title":"Enhancing analysis of diadochokinetic speech using deep neural networks","year":2024,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Voice and Speech Disorders","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Government of Ontario; National Institutes of Health; National Science Foundation; Ministry of Science and Technology, Israel; Ontario Brain Institute; United States-Israel Binational Science Foundation","keywords":"Computer science; Speech recognition; Deep learning; Artificial intelligence; Convolutional neural network; Artificial neural network; Pattern recognition (psychology)","score_opus":0.011068829136460576,"score_gpt":0.2895941880896504,"score_spread":0.2785253589531898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402127086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29561508,0.00270131,0.6894016,0.00065096194,0.0004345847,0.00010469387,0.0014703241,0.0014248195,0.008196646],"genre_scores_gemma":[0.9004371,0.0013411987,0.087762654,0.00022265996,0.00016712824,0.00006367948,0.001577638,0.00019476426,0.008233161],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9999107,0.000014158166,0.0000052783794,0.000023890003,0.000030003466,0.00001589347],"domain_scores_gemma":[0.9998441,0.00007615215,0.000011553135,0.00000979271,0.000048763133,0.000009646499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017539183,0.00062127673,0.00029136115,0.00043547238,0.00014290378,0.00042483094,0.00019470988,0.00034753463,0.0019760844],"category_scores_gemma":[0.0006590663,0.00015243352,0.00039503007,0.00022666526,0.0001289637,0.00036301411,0.0004146421,0.00047491695,0.00084236416],"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":[0.0009053054,0.0002547856,0.005902353,0.00038088654,0.00015566965,0.0006062699,0.00014967978,0.06291775,0.27276957,0.001543533,0.005216419,0.6491977],"study_design_scores_gemma":[0.000020533977,0.000119542034,0.016215436,0.00005479081,0.000075605836,0.0005279258,0.000114311304,0.93975073,0.036741838,0.002389658,0.0039564827,0.000033054635],"about_ca_topic_score_codex":0.0019983763,"about_ca_topic_score_gemma":0.0046766615,"teacher_disagreement_score":0.0019983763,"about_ca_system_score_codex":0.00015130472,"about_ca_system_score_gemma":0.00029202361,"threshold_uncertainty_score":0.006610632},"labels":[],"label_agreement":null},{"id":"W4402910001","doi":"10.1016/j.csl.2024.101723","title":"Speech Generation for Indigenous Language Education","year":2024,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University nuhelot'ine thaiyots'i nistameyimâkanak Blue Quills; National Research Council Canada","funders":"UK Research and Innovation","keywords":"Computer science; Indigenous; Natural language processing; Linguistics; Artificial intelligence; Speech recognition; Ecology","score_opus":0.04128638080843477,"score_gpt":0.4452927727766668,"score_spread":0.404006391968232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402910001","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035012595,0.0011126595,0.86602265,0.0021903957,0.0004111069,0.00047046287,0.0019578296,0.031973634,0.060848664],"genre_scores_gemma":[0.38304096,0.0013499921,0.55658066,0.0006845545,0.00016276895,0.00068462925,0.004962873,0.004882764,0.047650795],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986914,0.00042874453,0.00009564393,0.00021786166,0.00047374982,0.000092761424],"domain_scores_gemma":[0.9982047,0.0008624113,0.000062394356,0.00032341515,0.0004327707,0.00011427708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018877652,0.00055296783,0.000360048,0.0006703068,0.00075699174,0.0017455402,0.0011678543,0.00097144186,0.019251807],"category_scores_gemma":[0.005535805,0.00029869424,0.00061040674,0.0004346177,0.00074610114,0.0018911571,0.0033214176,0.0011523163,0.0048505603],"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":[0.0002768289,0.00014225939,0.0023347966,0.001093188,0.00006352599,0.00055343006,0.0048318035,0.018533284,0.05926726,0.046214398,0.03237985,0.8343093],"study_design_scores_gemma":[0.00014336035,0.00047914055,0.006114885,0.0006365014,0.00013709931,0.0014016936,0.0028956232,0.17625742,0.090485394,0.07777399,0.64347804,0.0001968481],"about_ca_topic_score_codex":0.0063629975,"about_ca_topic_score_gemma":0.006753643,"teacher_disagreement_score":0.019251807,"about_ca_system_score_codex":0.0010945429,"about_ca_system_score_gemma":0.0019916366,"threshold_uncertainty_score":0.06440365},"labels":[],"label_agreement":null},{"id":"W4410431605","doi":"10.1016/j.csl.2025.101815","title":"BERSting at the screams: A benchmark for distanced, emotional and shouted speech recognition","year":2025,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Benchmark (surveying); Speech recognition; Emotion recognition; Natural language processing","score_opus":0.01565752871258395,"score_gpt":0.2604487816432463,"score_spread":0.24479125293066237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410431605","genre_codex":"dataset","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36261338,0.026697999,0.04577526,0.003958049,0.007957797,0.0029523156,0.44590357,0.04962753,0.05451411],"genre_scores_gemma":[0.113848,0.0019041498,0.038661715,0.0009613886,0.00050866744,0.001184652,0.82801414,0.001057448,0.013859823],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99349535,0.0014371929,0.00084564066,0.0014812791,0.0021413222,0.00059928227],"domain_scores_gemma":[0.99509686,0.0012965263,0.0003247551,0.001179124,0.0015696748,0.0005329923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034898524,0.0051511494,0.0025513822,0.00336269,0.0017956507,0.0028002532,0.004288053,0.004305886,0.0066460217],"category_scores_gemma":[0.008632181,0.00050602684,0.0017593572,0.0024276322,0.0012889127,0.0030892014,0.004704046,0.0027391673,0.016798126],"study_design_candidate":"simulation_or_modeling","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":[0.0034471988,0.002146336,0.008837781,0.005208268,0.00073471986,0.0018943951,0.0009301549,0.01627897,0.031835083,0.0017994675,0.56688875,0.35999885],"study_design_scores_gemma":[0.0014899498,0.004714636,0.10420149,0.0019611141,0.0007180106,0.009171566,0.006402718,0.21858467,0.08512628,0.006732907,0.5599101,0.0009865361],"about_ca_topic_score_codex":0.018667305,"about_ca_topic_score_gemma":0.029806416,"teacher_disagreement_score":0.018667305,"about_ca_system_score_codex":0.0016036388,"about_ca_system_score_gemma":0.001604863,"threshold_uncertainty_score":0.037117302},"labels":[],"label_agreement":null},{"id":"W4416581044","doi":"10.1016/j.csl.2025.101907","title":"A robust framework for noisy speech recognition using Frequency-Guided-Swin Transformer","year":2025,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"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 Moncton","funders":"","keywords":"Transformer; Robustness (evolution); Convolutional neural network; Word error rate; Pattern recognition (psychology); Deep neural networks; Artificial neural network; Deep learning","score_opus":0.06383290841893033,"score_gpt":0.3086372540781378,"score_spread":0.24480434565920747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416581044","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008472891,0.00005042122,0.998248,0.000014367496,0.000014308876,0.000011267566,0.000024618235,0.00055187027,0.0002378258],"genre_scores_gemma":[0.117629245,0.0003745622,0.8753018,0.00011976398,0.000095298215,0.00010537129,0.00053271774,0.0005972671,0.005244052],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922323,0.00013927388,0.000050814928,0.00016864261,0.00032788454,0.000089994035],"domain_scores_gemma":[0.99957544,0.00010406097,0.000040217452,0.000102350976,0.00014804935,0.000029898307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009314664,0.0010555931,0.0011959432,0.00089224364,0.00048601444,0.0012587963,0.0017807878,0.0010283632,0.004593009],"category_scores_gemma":[0.0013630963,0.0005430847,0.0012037983,0.0006182271,0.0006864148,0.0013355898,0.0015502844,0.0011649716,0.0035049405],"study_design_candidate":"simulation_or_modeling","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":[0.000702434,0.00018609241,0.00043915506,0.0002168583,0.00013183411,0.000328314,0.00011696497,0.10735609,0.23751782,0.04961456,0.0047033085,0.5986866],"study_design_scores_gemma":[0.000014622891,0.00008007599,0.0001606889,0.000011332242,0.000031200645,0.00018292661,0.000020700198,0.9416095,0.04529644,0.007413917,0.0051535596,0.000025000158],"about_ca_topic_score_codex":0.0039000285,"about_ca_topic_score_gemma":0.0059554204,"teacher_disagreement_score":0.004593009,"about_ca_system_score_codex":0.0004959121,"about_ca_system_score_gemma":0.0010082398,"threshold_uncertainty_score":0.015365183},"labels":[],"label_agreement":null},{"id":"W4417072973","doi":"10.1016/j.csl.2025.101923","title":"Enhanced audio-visual speech enhancement with posterior sampling methods in recurrent variational autoencoders","year":2025,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Speech enhancement; Inference; Intelligibility (philosophy); Sampling (signal processing); Autoencoder; Pattern recognition (psychology); Noise reduction; Posterior probability","score_opus":0.015556743825154234,"score_gpt":0.35044631308874546,"score_spread":0.33488956926359126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417072973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011742771,0.0002998085,0.98654085,0.00006448277,0.00003806846,0.000015700469,0.000029171793,0.00047479596,0.00079437834],"genre_scores_gemma":[0.4597911,0.0006398692,0.53346395,0.00017738869,0.00008607925,0.000088051,0.0002991555,0.00031370815,0.00514064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969053,0.00008833695,0.000016142018,0.00006679083,0.00011469203,0.00002360956],"domain_scores_gemma":[0.9994355,0.00033227663,0.000039076647,0.000055958863,0.0001140837,0.00002308303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089138537,0.0007595244,0.00051950436,0.00026926238,0.0001748725,0.00050356326,0.00070900994,0.0005926199,0.0013792516],"category_scores_gemma":[0.002053775,0.000288299,0.0007402326,0.0001864916,0.00039539777,0.00074064045,0.0008550411,0.0010003643,0.00059693126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003507142,0.00012192072,0.0008135233,0.00023937518,0.00014904512,0.00022916135,0.00021953821,0.51933414,0.11673116,0.012276692,0.0016606688,0.34787405],"study_design_scores_gemma":[0.000006519696,0.000039094124,0.0001369721,0.000008642064,0.000012995166,0.00005381875,0.000008520439,0.9856103,0.011700739,0.0016026825,0.00081003323,0.000009636139],"about_ca_topic_score_codex":0.0018007477,"about_ca_topic_score_gemma":0.0031882918,"teacher_disagreement_score":0.0018007477,"about_ca_system_score_codex":0.00023285327,"about_ca_system_score_gemma":0.0004802164,"threshold_uncertainty_score":0.004714191},"labels":[],"label_agreement":null}]}