{"id":"W3206189675","doi":"10.1109/icassp43922.2022.9747814","title":"Large-Scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Generalizability theory; Computer science; Speech recognition; Word error rate; Speaker recognition; Artificial intelligence; Representation (politics); Artificial neural network; Scale (ratio); Feature (linguistics); Pattern recognition (psychology); Machine learning; Mathematics","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":[0.002093885,0.0009885173,0.0008306139,0.0004783709,0.0003475823,0.0005541008,0.001361725,0.0009018201,0.001583271],"category_scores_gemma":[0.003927257,0.0002922473,0.0006037761,0.0003806614,0.0004801858,0.0016079,0.001303852,0.001341132,0.001739394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004384193,"about_ca_system_score_gemma":0.0007770734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002283589,"about_ca_topic_score_gemma":0.003038761,"domain_scores_codex":[0.9984571,0.0005954118,0.0000569385,0.0004752613,0.000318901,0.00009643196],"domain_scores_gemma":[0.998173,0.0005595586,0.0001298114,0.0006718581,0.0004096714,0.00005604734],"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":[0.0004968165,0.0003324261,0.00155584,0.0001338944,0.0001383094,0.00006363054,0.0001167907,0.09967714,0.04211066,0.001947413,0.008189127,0.845238],"study_design_scores_gemma":[0.00001536351,0.0001166225,0.0008712773,0.000008662662,0.0000237253,0.00006243444,0.00002491709,0.9729192,0.02320033,0.001528821,0.001212984,0.00001573835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1059898,0.001567086,0.8789302,0.0002610617,0.0002010005,0.0001432184,0.0005612142,0.00980564,0.002540854],"genre_scores_gemma":[0.8104081,0.0003546148,0.1809795,0.0002058219,0.0001192573,0.0002120805,0.003008436,0.0002903043,0.004421971],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002283589,"threshold_uncertainty_score":0.01107365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0517667352431102,"score_gpt":0.3075118367600685,"score_spread":0.2557451015169583,"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."}}