{"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50798374,0.00050005014,0.47401473,0.0005697096,0.00026701737,0.00014229616,0.00053084316,0.002322218,0.0136694545],"genre_scores_gemma":[0.95254743,0.000098428696,0.044663645,0.00010121784,0.00008637894,0.000039353476,0.00026257467,0.00004888753,0.0021520425],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99936646,0.0002113035,0.000029263974,0.00015623291,0.00016817675,0.00006851377],"domain_scores_gemma":[0.9983028,0.000829607,0.00017866834,0.0001856755,0.00039961288,0.00010361497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090872997,0.000607422,0.00046083162,0.00061221956,0.00024361837,0.0009381018,0.00040575885,0.0005768479,0.0017164013],"category_scores_gemma":[0.0044481875,0.00015312433,0.00041001494,0.00021750294,0.00029339828,0.0011095882,0.000703267,0.00085147674,0.0010659294],"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":[0.0014908962,0.0008537192,0.055604793,0.00030722198,0.00031311144,0.00031982703,0.0009743663,0.01910137,0.23572405,0.0031040187,0.0042039286,0.6780028],"study_design_scores_gemma":[0.000029058328,0.00055790716,0.07537885,0.000059536433,0.00017505474,0.00039318227,0.00046897726,0.8183023,0.09097374,0.00914123,0.0044000093,0.000120128774],"about_ca_topic_score_codex":0.0005313936,"about_ca_topic_score_gemma":0.001024279,"teacher_disagreement_score":0.0017164013,"about_ca_system_score_codex":0.00017467437,"about_ca_system_score_gemma":0.00018277674,"threshold_uncertainty_score":0.005741954},"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":"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":[0.44592604,0.0016474805,0.53915906,0.00031915776,0.00029839983,0.00008380743,0.00023832406,0.0018452727,0.010482445],"genre_scores_gemma":[0.6864052,0.0006716325,0.30688393,0.000120115415,0.00005869689,0.000029352852,0.00022638871,0.000103914164,0.005500853],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99987924,0.000032656877,0.000005138135,0.000021862194,0.00004779844,0.000013248765],"domain_scores_gemma":[0.99975115,0.00012626976,0.000017688304,0.00003054965,0.000054631055,0.000019850886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002230256,0.00036257107,0.00028441625,0.00018211587,0.00012821904,0.0002687451,0.00039614405,0.0005036636,0.0028452806],"category_scores_gemma":[0.0005959456,0.00013171376,0.0002336018,0.00013241658,0.0002510903,0.00042187222,0.00055335404,0.0003632869,0.00057957746],"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":[0.0012610687,0.00008462797,0.0003379442,0.00016082972,0.00003756379,0.00029358667,0.000093945346,0.0068860883,0.8671689,0.0012377469,0.0011218301,0.12131588],"study_design_scores_gemma":[0.00010464527,0.00054173684,0.0035694125,0.00004592369,0.00015841203,0.0019444667,0.00009000456,0.33256888,0.65346974,0.001025754,0.0064347293,0.00004629023],"about_ca_topic_score_codex":0.00040342292,"about_ca_topic_score_gemma":0.0011162913,"teacher_disagreement_score":0.0028452806,"about_ca_system_score_codex":0.000073112475,"about_ca_system_score_gemma":0.000113074464,"threshold_uncertainty_score":0.009518445},"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":"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":[0.25843817,0.0014190868,0.6176535,0.0017107035,0.0009227787,0.00055679475,0.0020079156,0.07908029,0.0382108],"genre_scores_gemma":[0.56843925,0.00042926558,0.40445915,0.00064493826,0.00008720976,0.00022362094,0.0013018969,0.0028164936,0.021598177],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99981576,0.000028085897,0.000007873681,0.000026817568,0.000093814495,0.000027718716],"domain_scores_gemma":[0.99968755,0.00009738121,0.00001264909,0.00003157829,0.00012976133,0.00004108131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005219576,0.0007179675,0.00032242484,0.0003136628,0.00028696898,0.00033394826,0.0007653812,0.0006927355,0.013985882],"category_scores_gemma":[0.00081716385,0.0002068859,0.00016300305,0.00027559607,0.0002241356,0.00049006636,0.000430717,0.00044505083,0.003071228],"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":[0.0028198613,0.000314797,0.0021008118,0.00047706437,0.00010224882,0.0018731258,0.000682911,0.0096941935,0.54950774,0.002196101,0.054555673,0.37567535],"study_design_scores_gemma":[0.00060976605,0.0008467612,0.0075807655,0.00018135917,0.000091016045,0.0023133163,0.00030218286,0.3169936,0.5837184,0.0011615441,0.08604828,0.00015304692],"about_ca_topic_score_codex":0.007253439,"about_ca_topic_score_gemma":0.011093394,"teacher_disagreement_score":0.013985882,"about_ca_system_score_codex":0.0002471433,"about_ca_system_score_gemma":0.00046572307,"threshold_uncertainty_score":0.04678738},"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":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069652554,0.0008576934,0.004988508,0.00037152207,0.00035673837,0.0006658372,0.9645161,0.0034464092,0.017831953],"genre_scores_gemma":[0.0066012037,0.00023789672,0.007931275,0.00017163024,0.000075454285,0.0012061711,0.97864944,0.0008416008,0.004285385],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987,0.000283305,0.00023449055,0.00043021332,0.00024147076,0.000110401445],"domain_scores_gemma":[0.99766076,0.0006541464,0.0001287325,0.0004579668,0.00085019297,0.00024818332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012981787,0.0017172267,0.0011410215,0.006586926,0.001998093,0.0024251,0.0018694086,0.0014373548,0.112173274],"category_scores_gemma":[0.0030399067,0.00089333626,0.00057758205,0.0068379464,0.00083170965,0.001637037,0.003091621,0.0021273931,0.08400889],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047305954,0.00025275335,0.0022206868,0.0025500297,0.000059591308,0.0006487863,0.00072059396,0.0004721991,0.014815002,0.0037327656,0.93061376,0.043440834],"study_design_scores_gemma":[0.00031154868,0.00007107376,0.014349115,0.00034560298,0.000065582884,0.001230951,0.0007640599,0.0010849579,0.0064267074,0.0017157713,0.9735454,0.00008917988],"about_ca_topic_score_codex":0.023411853,"about_ca_topic_score_gemma":0.036818285,"teacher_disagreement_score":0.112173274,"about_ca_system_score_codex":0.0010127944,"about_ca_system_score_gemma":0.0029451656,"threshold_uncertainty_score":0.37525702},"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":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007046253,0.0013748158,0.5649403,0.0005145205,0.0009714546,0.00055779505,0.07214409,0.32293952,0.029511377],"genre_scores_gemma":[0.051030193,0.00093684276,0.7952714,0.00056639704,0.00028799137,0.0035572292,0.06625311,0.045326784,0.03677006],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99646723,0.0010419195,0.00058862806,0.0005176717,0.001177848,0.00020666247],"domain_scores_gemma":[0.98824525,0.007116379,0.00061158545,0.0015269222,0.0018190907,0.000680852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005231069,0.002435758,0.0015082202,0.005326773,0.0011050985,0.0037756537,0.0025583848,0.0012755801,0.11702954],"category_scores_gemma":[0.021544052,0.0014549888,0.0012411542,0.0035587514,0.0009521423,0.0050684074,0.0060345945,0.0021987245,0.06459254],"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":[0.0015225383,0.0003143041,0.0052622957,0.001857497,0.00022911667,0.0008242495,0.0011522374,0.0014257205,0.026919113,0.018089049,0.3961413,0.5462626],"study_design_scores_gemma":[0.00047896768,0.00043795008,0.018601332,0.0011635085,0.00026465388,0.0044324924,0.0010325465,0.03024904,0.06491951,0.08383408,0.7942215,0.00036447702],"about_ca_topic_score_codex":0.0017834175,"about_ca_topic_score_gemma":0.0034003446,"teacher_disagreement_score":0.11702954,"about_ca_system_score_codex":0.00034420498,"about_ca_system_score_gemma":0.0016299612,"threshold_uncertainty_score":0.39150286},"labels":[],"label_agreement":null}]}