{"id":"W3131901777","doi":"10.71781/10868","title":"Advances in deep learning methods for speech recognition and understanding","year":2020,"lang":"en","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Samsung; Compute Canada","keywords":"Speech recognition; Deep learning; Computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0003013888,0.0002496166,0.0003155492,0.0003692694,0.002051938,0.0001098198,0.0002885277,0.000251654,0.00001180151],"category_scores_gemma":[0.0002119885,0.0002973099,0.0001412129,0.0003401324,0.00005178751,0.000771205,0.00007741761,0.0003217255,0.00001107816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002012664,"about_ca_system_score_gemma":0.000302753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004642022,"about_ca_topic_score_gemma":0.001710034,"domain_scores_codex":[0.9984533,0.0001863332,0.0002730827,0.0005862378,0.0002420362,0.0002590434],"domain_scores_gemma":[0.9989465,0.0003878898,0.0002515293,0.0001358447,0.0001141626,0.0001640032],"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":[0.0002491553,0.00003592152,0.0001867045,0.0001785139,0.00004806539,0.0002761437,0.009643384,0.00003719914,0.002286144,0.009292719,0.00001659795,0.9777495],"study_design_scores_gemma":[0.006918554,0.0008631307,0.004451214,0.00234762,0.0006811785,0.002097799,0.1920554,0.3055323,0.1162957,0.1557788,0.2087455,0.004232903],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01737462,0.03379069,0.8482031,0.000548724,0.001662567,0.001056736,0.00001993907,0.0004249743,0.09691861],"genre_scores_gemma":[0.09244486,0.01207297,0.886206,0.000271773,0.00026213,0.0001609743,0.0008840359,0.0000791464,0.007618082],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9735165,"threshold_uncertainty_score":0.9999479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02693497538385669,"score_gpt":0.2428677935263863,"score_spread":0.2159328181425296,"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."}}