{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009956871,0.001142042,0.000446097,0.0006004608,0.0003327714,0.0007022741,0.001633035,0.001194539,0.003638224],"category_scores_gemma":[0.002892019,0.0003442519,0.0005998356,0.0005035998,0.0004787466,0.001892033,0.001610682,0.002231785,0.001463962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001111132,"about_ca_system_score_gemma":0.0008828578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006634667,"about_ca_topic_score_gemma":0.01266373,"domain_scores_codex":[0.9996407,0.00008759491,0.00001355969,0.0001327832,0.00006456072,0.00006073775],"domain_scores_gemma":[0.9993129,0.0003332647,0.00004621473,0.0001207431,0.0001200559,0.00006676802],"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":[0.0005965462,0.0002945796,0.003272614,0.0002251188,0.0001388996,0.000174535,0.0002162747,0.09910794,0.03365165,0.01268228,0.02080517,0.8288345],"study_design_scores_gemma":[0.00001946077,0.0000818363,0.001132147,0.00002802463,0.00005509529,0.00007558068,0.00002875846,0.9594343,0.01371321,0.01995497,0.005462673,0.00001401445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05987217,0.004469967,0.91954,0.001831131,0.0005016231,0.0001137075,0.0008461941,0.00527543,0.007549725],"genre_scores_gemma":[0.8196481,0.001508637,0.163645,0.0008970735,0.0002443323,0.0001553434,0.002160926,0.0002953222,0.01144527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006634667,"threshold_uncertainty_score":0.01319206,"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."}}