{"id":"W2147094156","doi":"10.1109/asru.2007.4430179","title":"Interpolative variable frame rate transmission of speech features for distributed speech recognition","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"","keywords":"Computer science; Speech recognition; Voice activity detection; Speech coding; Word error rate; Linear predictive coding; Codec2; Frame (networking); Speech processing; Artificial intelligence; Computer network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001056263,0.000162502,0.000243804,0.0001811716,0.00008863883,0.00007155129,0.0003729827,0.0001556511,0.0003852238],"category_scores_gemma":[0.000249043,0.0001350851,0.0001324536,0.0005173738,0.00003907335,0.0004118108,0.00004305117,0.0001316322,0.00002945017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004246903,"about_ca_system_score_gemma":0.00004277773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004997057,"about_ca_topic_score_gemma":0.00001155382,"domain_scores_codex":[0.9986846,0.00006695762,0.0003825312,0.0003520072,0.000205104,0.0003087959],"domain_scores_gemma":[0.998367,0.0007486948,0.0001432047,0.0002525712,0.0003625672,0.0001260111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001312987,0.0001090599,0.00002877129,0.00003461701,0.00003586185,0.000006805077,0.0001505715,6.460661e-7,0.03342684,0.00413244,0.001540174,0.9604029],"study_design_scores_gemma":[0.0006818612,0.000179208,0.0008729584,0.00009990948,0.00002114345,0.00003269202,0.0001165698,0.01006502,0.934486,0.04696422,0.006235876,0.0002445924],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005731674,0.0000237064,0.9792707,0.0004894123,0.0002159556,0.000391171,0.00007492031,0.0001583427,0.01364414],"genre_scores_gemma":[0.1065267,0.00001189624,0.8920864,0.0003425744,0.00007943845,0.00001341992,0.0000924163,0.00001309005,0.0008339951],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9601583,"threshold_uncertainty_score":0.5508611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02457184801513324,"score_gpt":0.2716059338041716,"score_spread":0.2470340857890383,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}