{"id":"W4313148067","doi":"10.1007/978-3-031-20980-2_21","title":"CRIM’s Speech Recognition System for OpenASR21 Evaluation with Conformer and Voice Activity Detector Embeddings","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speech recognition; Computer science; Hidden Markov model; Mel-frequency cepstrum; Word error rate; Sentence; Artificial intelligence; Language model; Natural language processing; Pattern recognition (psychology); Feature extraction","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004252063,0.002417407,0.001518246,0.001849792,0.001055196,0.002126771,0.002235066,0.002083519,0.02475068],"category_scores_gemma":[0.005448291,0.000636573,0.000938728,0.001089944,0.0004750947,0.001914501,0.002038772,0.001396832,0.0330814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008781466,"about_ca_system_score_gemma":0.001475604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009911119,"about_ca_topic_score_gemma":0.01058399,"domain_scores_codex":[0.9964848,0.0008647743,0.0003015311,0.0008113428,0.001251881,0.0002857075],"domain_scores_gemma":[0.9968926,0.0006175333,0.00008138618,0.0006786209,0.001495208,0.0002346227],"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":[0.002768117,0.0007242631,0.00234977,0.0007792007,0.0003885391,0.0005855235,0.0002570503,0.007412699,0.07175879,0.002112895,0.2082953,0.7025677],"study_design_scores_gemma":[0.001395103,0.002922704,0.01792307,0.0002207881,0.000585229,0.00243326,0.0008270835,0.3018568,0.3879612,0.003666364,0.2797527,0.0004557008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1969144,0.003900411,0.3641807,0.001151705,0.004588709,0.003041306,0.05567,0.3011369,0.06941584],"genre_scores_gemma":[0.3020822,0.0009843989,0.3987801,0.0009339107,0.0004558463,0.002728822,0.2033932,0.01229533,0.0783462],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02475068,"threshold_uncertainty_score":0.08279926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04380244650141289,"score_gpt":0.2745464862934964,"score_spread":0.2307440397920835,"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."}}