{"id":"W2912129510","doi":"10.1109/icassp.2019.8683565","title":"Exploring Attention Mechanism for Acoustic-based Classification of Speech Utterances into System-directed and Non-system-directed","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Phrase; Mechanism (biology); Speech recognition; Word (group theory); Convolutional neural network; Artificial intelligence; Recurrent neural network; Natural language processing; Artificial neural network; Linguistics","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":[0.0007800258,0.0004201423,0.0007991893,0.0005726684,0.0001479443,0.0002942575,0.0007429498,0.0003280168,0.000008903488],"category_scores_gemma":[0.0001304776,0.0003936463,0.0002477936,0.0003404282,0.000038787,0.0004070888,0.0002722865,0.0002186157,0.00003042999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002468483,"about_ca_system_score_gemma":0.0001739755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002071188,"about_ca_topic_score_gemma":0.00004457109,"domain_scores_codex":[0.9969471,0.0002059049,0.0008865625,0.001115316,0.0005291132,0.0003160258],"domain_scores_gemma":[0.9966664,0.0004286196,0.0007685436,0.00099542,0.001023309,0.0001177039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004136003,0.0005682413,0.001116218,0.05384628,0.001069356,0.00003394574,0.001675709,0.0004462423,0.5582599,0.07057232,0.001170515,0.3108277],"study_design_scores_gemma":[0.0007161662,0.00007217434,0.002344372,0.002121213,0.0001094612,0.000009216691,0.0005212387,0.8896599,0.1034578,0.0005058596,0.00002209535,0.0004604311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09658328,0.00003539258,0.895867,0.0001969963,0.002027873,0.001861421,0.00006004554,0.001515011,0.001852999],"genre_scores_gemma":[0.7623379,0.00002357877,0.2365647,0.0000262118,0.0001234518,0.0007076742,0.00007580603,0.00003136664,0.0001093725],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8892137,"threshold_uncertainty_score":0.9998515,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08203991703136106,"score_gpt":0.2662062726164808,"score_spread":0.1841663555851198,"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."}}