{"id":"W3082779874","doi":"","title":"Knowing What to Listen to: Early Attention for Deep Speech Representation Learning.","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Robustness (evolution); Speech recognition; Deep learning; Speaker recognition; Artificial intelligence; Deep neural networks; Speech processing; Task (project management); Emotion recognition; Feature learning","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":[0.0002572483,0.0002527558,0.000312284,0.0003739296,0.0002007696,0.0007001158,0.001122342,0.0001967262,0.0000374881],"category_scores_gemma":[0.00028762,0.0003223012,0.0003149686,0.0008144584,0.00001926655,0.0008813711,0.001184444,0.0003277678,0.0005760982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001819194,"about_ca_system_score_gemma":0.00006428472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009949366,"about_ca_topic_score_gemma":0.00004519879,"domain_scores_codex":[0.9978266,0.0001624443,0.000226137,0.001323848,0.0001424201,0.0003185367],"domain_scores_gemma":[0.9983466,0.0002023002,0.0001704695,0.0006444062,0.00030299,0.0003331797],"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":[0.0004731559,0.0002887703,0.009186154,0.0003616168,0.0005117913,0.0007779793,0.00540678,0.08522582,0.003355498,0.03156098,0.002595219,0.8602563],"study_design_scores_gemma":[0.001452754,0.0006395133,0.01655869,0.0008370689,0.0002930063,0.0000151999,0.002946384,0.9242854,0.006437978,0.03188239,0.01261948,0.002032105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2085718,0.00001276212,0.7867916,0.00137477,0.0007773846,0.0007551378,0.000004323093,0.0002903236,0.001421904],"genre_scores_gemma":[0.9502219,0.00007081529,0.04471775,0.0005917423,0.0001924402,0.00001108271,0.00003712311,0.00003158623,0.004125575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8582242,"threshold_uncertainty_score":0.9999229,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1231209017771726,"score_gpt":0.2327127579931186,"score_spread":0.1095918562159459,"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."}}