{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002196184,0.0004635335,0.0005107897,0.0007154375,0.000530671,0.0007121902,0.001166817,0.0002135743,0.0001026692],"category_scores_gemma":[0.0001906726,0.0004078578,0.00009888218,0.0004406235,0.0002971285,0.001267534,0.0005197676,0.0004938811,0.00002331376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000654576,"about_ca_system_score_gemma":0.0006229837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000475005,"about_ca_topic_score_gemma":0.0001266884,"domain_scores_codex":[0.9962498,0.00008471597,0.0003775639,0.001467553,0.001326179,0.0004941721],"domain_scores_gemma":[0.997351,0.0007425577,0.0004067122,0.0006913022,0.000645635,0.0001628242],"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":[0.00003962613,0.00001638805,0.000004421893,0.00009836348,0.00001714772,0.00001665894,0.0002336373,0.0001103613,0.0004873446,0.0004034794,0.000009369009,0.9985632],"study_design_scores_gemma":[0.001936956,0.001074298,0.0001758818,0.001071467,0.0001412278,0.0009124402,0.00000588352,0.8680178,0.1005729,0.02093835,0.003404863,0.001747899],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003107201,0.0001187487,0.9891456,0.0003319299,0.001042091,0.001668056,0.00003808792,0.0001722046,0.004376026],"genre_scores_gemma":[0.3276205,0.00003079379,0.6706055,0.000821221,0.0003477271,0.0003142986,0.00002964818,0.0000661184,0.0001640902],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9968153,"threshold_uncertainty_score":0.9998373,"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."}}