{"id":"W2935542736","doi":"10.21437/interspeech.2019-2605","title":"Learning Problem-Agnostic Speech Representations from Multiple Self-Supervised Tasks","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Compute Canada","keywords":"Computer science; Encoder; Discriminator; Artificial intelligence; Speech recognition; Machine learning; Supervised learning; Construct (python library); SIGNAL (programming language); Adaptation (eye); Identity (music); Pattern recognition (psychology); Artificial neural network; Psychology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002548915,0.001343162,0.00110419,0.0005917823,0.0004043057,0.0009391896,0.00190681,0.001491296,0.001642489],"category_scores_gemma":[0.005702505,0.0005980774,0.0009562192,0.0004802359,0.001053828,0.00193277,0.002311302,0.002193042,0.0009964919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005041586,"about_ca_system_score_gemma":0.0009171802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006338095,"about_ca_topic_score_gemma":0.001100032,"domain_scores_codex":[0.9986492,0.0004982452,0.00006146247,0.000478635,0.0001995879,0.0001128949],"domain_scores_gemma":[0.9970967,0.001181827,0.0003184176,0.0008591378,0.0003774407,0.0001665951],"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":[0.0004233091,0.0005579426,0.002491941,0.0003196426,0.0002520424,0.0001415551,0.0003501169,0.4103571,0.0300904,0.0112814,0.003625687,0.5401089],"study_design_scores_gemma":[0.00001498613,0.00007346705,0.0003921102,0.000009258678,0.00001440102,0.00003935105,0.00002565302,0.9842893,0.00586341,0.008743944,0.0005242616,0.000009768002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04110538,0.0001868806,0.9561185,0.0001786373,0.00004100985,0.00008329914,0.00007992158,0.0009743631,0.001232031],"genre_scores_gemma":[0.6985314,0.0001901766,0.294868,0.000214236,0.0001708531,0.0002711482,0.0007419251,0.0002749928,0.004737321],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002548915,"threshold_uncertainty_score":0.01348013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03083472838545893,"score_gpt":0.2633205265083643,"score_spread":0.2324857981229054,"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."}}