{"id":"W4224917505","doi":"10.1109/icassp43922.2022.9747452","title":"Robust Self-Supervised Speaker Representation Learning Via Instance Mix Regularization","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":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Embedding; Regularization (linguistics); Speech recognition; Feature learning; Utterance; Artificial intelligence; Supervised learning; Speaker recognition; Pattern recognition (psychology); Machine learning; Artificial neural network","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":[0.001984954,0.001325114,0.001184392,0.0006350514,0.0003115967,0.0006624209,0.001969204,0.001163132,0.0016831],"category_scores_gemma":[0.003024111,0.0004639419,0.001032923,0.0004343549,0.0006802671,0.001403682,0.001700943,0.002203779,0.001290479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005024914,"about_ca_system_score_gemma":0.0006801705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001605278,"about_ca_topic_score_gemma":0.002260471,"domain_scores_codex":[0.9986709,0.0005022391,0.00004498049,0.0004166834,0.0002645594,0.0001006714],"domain_scores_gemma":[0.9987677,0.0004412141,0.0001350467,0.0003067312,0.0002921967,0.0000571997],"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":[0.0005768851,0.0003358321,0.001747968,0.0001795063,0.0003135392,0.000126038,0.000204944,0.2797608,0.04757734,0.007578396,0.013002,0.6485968],"study_design_scores_gemma":[0.000008197692,0.000026901,0.0001406438,0.000002990023,0.000007998146,0.00002992832,0.0000061659,0.9930233,0.005055129,0.001307813,0.0003839824,0.000006974896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03378,0.0003551151,0.9606712,0.000158762,0.00005726797,0.0000559339,0.0001680801,0.003697885,0.001055686],"genre_scores_gemma":[0.5878234,0.0002576636,0.3992213,0.000433205,0.0001585091,0.0002225801,0.002246747,0.0006814335,0.008955092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001984954,"threshold_uncertainty_score":0.01049757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05941694244909695,"score_gpt":0.2801079894117903,"score_spread":0.2206910469626934,"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."}}