{"id":"W4319862473","doi":"10.1109/slt54892.2023.10022470","title":"A Comprehensive Study on Self-Supervised Distillation for Speaker Representation Learning","year":2023,"lang":"en","type":"article","venue":"2022 IEEE Spoken Language Technology Workshop (SLT)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Benchmark (surveying); Representation (politics); Speaker recognition; Speech recognition; Artificial intelligence; Word error rate; Training set; Feature learning; Machine 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002943006,0.0002454442,0.0003295598,0.000897788,0.0003188644,0.0001039314,0.0006520097,0.0002176564,0.00007054593],"category_scores_gemma":[0.000397626,0.0002427816,0.0001271644,0.002473728,0.00005366149,0.0001977087,0.0001890111,0.000401829,0.0004165637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008617,"about_ca_system_score_gemma":0.00002715078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001408349,"about_ca_topic_score_gemma":0.00002396203,"domain_scores_codex":[0.9979411,0.0001537264,0.0003403005,0.0007766965,0.000349769,0.0004384246],"domain_scores_gemma":[0.9982219,0.0006486527,0.0001523953,0.0007808403,0.0001308392,0.00006538912],"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":[0.0001927889,0.0009185537,0.0127081,0.00007073492,0.0005075973,0.0008852363,0.02117847,0.001239682,0.02190286,0.003757234,0.01001195,0.9266268],"study_design_scores_gemma":[0.009836495,0.002268631,0.08648338,0.0002667756,0.0003175566,0.0001613379,0.181054,0.654527,0.04160882,0.005681688,0.01497062,0.002823694],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9601147,0.00006566082,0.03147535,0.00145728,0.0006073194,0.001358081,0.000008685136,0.003984778,0.0009281689],"genre_scores_gemma":[0.9856299,0.00002381792,0.01219423,0.0001997926,0.0001308638,0.0003718785,0.00005285049,0.00004126646,0.001355415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9238031,"threshold_uncertainty_score":0.9900348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03729401784374337,"score_gpt":0.322562182637299,"score_spread":0.2852681647935556,"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."}}