{"id":"W4289792473","doi":"10.1109/jstsp.2022.3196562","title":"L-Mix: A Latent-Level Instance Mixup Regularization for Robust Self-Supervised Speaker Representation Learning","year":2022,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Feature learning; Embedding; Speech recognition; Artificial intelligence; Regularization (linguistics); Speaker recognition; Pattern recognition (psychology); Supervised learning; Semi-supervised learning; Machine learning; Artificial neural network","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001939933,0.001341605,0.001051446,0.000580781,0.0003691588,0.0006908874,0.002018826,0.001367176,0.002138101],"category_scores_gemma":[0.002571766,0.0005171162,0.000944818,0.0004540051,0.0008398435,0.001605077,0.002189544,0.002122798,0.0009228358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000570661,"about_ca_system_score_gemma":0.0007113802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001310787,"about_ca_topic_score_gemma":0.00248825,"domain_scores_codex":[0.999103,0.0003559563,0.00003908723,0.0002203679,0.0002040007,0.00007771587],"domain_scores_gemma":[0.9992955,0.0002768331,0.00007709998,0.0001368074,0.0001605932,0.00005317177],"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":[0.0005876059,0.0004470185,0.002127016,0.000279909,0.0003855293,0.0001536733,0.000238183,0.376484,0.05039665,0.01451908,0.01204848,0.5423328],"study_design_scores_gemma":[0.000008474327,0.00004498434,0.0001136262,0.000005081355,0.000008859412,0.00002398964,0.000007194784,0.9937931,0.003900702,0.001539521,0.0005464081,0.000008115004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01986311,0.0003604475,0.9766258,0.0001569249,0.00004189181,0.00006192306,0.0001116627,0.00187751,0.0009008417],"genre_scores_gemma":[0.5141505,0.0003159496,0.4751974,0.0005936018,0.0001302796,0.0003959905,0.001231004,0.0006998032,0.007285496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002138101,"threshold_uncertainty_score":0.01025951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05517068553173211,"score_gpt":0.2693890251686757,"score_spread":0.2142183396369436,"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."}}