{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000512115,0.0001249922,0.0002176555,0.0001236169,0.0001331465,0.0001144513,0.0002092206,0.00008069701,0.0000455206],"category_scores_gemma":[0.000404676,0.0001321813,0.00007870443,0.000457394,0.00004538411,0.0003384283,0.00004798127,0.00006605405,0.00007676835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005113792,"about_ca_system_score_gemma":0.00007112487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001091706,"about_ca_topic_score_gemma":0.00001325297,"domain_scores_codex":[0.9986089,0.00009482128,0.0005139434,0.0004194764,0.0001723354,0.000190506],"domain_scores_gemma":[0.998448,0.000406026,0.0002235871,0.0003913361,0.0004618399,0.00006920256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006843539,0.000120326,0.00001149634,0.0006252218,0.00001613706,0.000008572615,0.0008526869,0.003603858,0.0217119,0.002561845,0.00006142941,0.9704197],"study_design_scores_gemma":[0.00004277518,0.0000451123,0.00003334685,0.0002274745,0.00002156292,0.00006988351,0.001465261,0.7375674,0.2591483,0.001214825,0.00005103456,0.0001129385],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03827154,0.0001287034,0.9596095,0.0002621573,0.0002271547,0.000474175,0.0000172527,0.0001310504,0.0008784269],"genre_scores_gemma":[0.6838922,0.00005378241,0.3155733,0.00003192226,0.0000379154,0.00009794378,0.00002571151,0.00001133085,0.0002758555],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9703068,"threshold_uncertainty_score":0.5390198,"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."}}