{"id":"W3178196694","doi":"10.18280/ria.350307","title":"Usage of Prosody Modification and Acoustic Adaptation for Robust Automatic Speech Recognition (ASR) System","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Prosody; Speech recognition; Naturalness; Computer science; Word error rate; Adaptation (eye); Speech processing; Psychology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005647936,0.0006089244,0.0004785586,0.0004466897,0.0002656134,0.0004985542,0.0007064937,0.000468162,0.002233882],"category_scores_gemma":[0.001211973,0.0002337513,0.0003564247,0.0002420017,0.0002384214,0.0005239235,0.000375751,0.0003976535,0.001443789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001474471,"about_ca_system_score_gemma":0.0002709166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008459605,"about_ca_topic_score_gemma":0.0007736565,"domain_scores_codex":[0.9993717,0.0001268494,0.00005520548,0.0002244128,0.0001785333,0.00004332711],"domain_scores_gemma":[0.9995646,0.0001218182,0.00005118243,0.00008050636,0.0001623727,0.00001942966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004434042,0.0001860134,0.002959638,0.0003330605,0.0000954225,0.0004483229,0.0003351662,0.005633428,0.6141489,0.0004493275,0.001133904,0.3738334],"study_design_scores_gemma":[0.0001029465,0.002190531,0.04493041,0.00009654164,0.0003798042,0.003963466,0.0002649782,0.1754484,0.7438934,0.0007392479,0.02782477,0.0001655549],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4411578,0.002551874,0.532701,0.0004094466,0.000308134,0.0005093566,0.0003772702,0.008373395,0.01361179],"genre_scores_gemma":[0.8124261,0.0008329252,0.1786425,0.0002614555,0.00007113344,0.0003407327,0.0005530345,0.000308742,0.006563337],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002233882,"threshold_uncertainty_score":0.007473111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1053857366578215,"score_gpt":0.2779478103906228,"score_spread":0.1725620737328013,"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."}}