{"id":"W2902368158","doi":"10.21437/interspeech.2019-2380","title":"Learning Speaker Representations with Mutual Information","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Discriminator; Mutual information; Computer science; Artificial intelligence; Encoder; Speech recognition; Feature learning; Sentence; Joint probability distribution; Feature (linguistics); Pattern recognition (psychology); Natural language processing; Mathematics; Linguistics; Statistics","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":[0.002654542,0.001323784,0.001100734,0.0009868672,0.0003893807,0.001034081,0.001144304,0.001453185,0.001887867],"category_scores_gemma":[0.006866603,0.0007599809,0.001131726,0.0006616054,0.001023804,0.002250113,0.002593673,0.002327503,0.0009766583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007456896,"about_ca_system_score_gemma":0.0007195251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001087916,"about_ca_topic_score_gemma":0.001335456,"domain_scores_codex":[0.9981029,0.0008632971,0.00007077715,0.0004641004,0.0003659642,0.0001329404],"domain_scores_gemma":[0.9974902,0.001613065,0.0002525974,0.0003521527,0.0002195576,0.00007258334],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003738976,0.0001229998,0.001726107,0.0001477235,0.000303069,0.0001226126,0.0002325636,0.6318833,0.01246005,0.02172134,0.004171842,0.3267345],"study_design_scores_gemma":[0.000007813671,0.00003632643,0.0002861978,0.000009209863,0.00001934201,0.00004507827,0.00001033267,0.9826133,0.002602933,0.0138716,0.000484275,0.00001368186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02308396,0.0003385625,0.9737002,0.0002745757,0.00002880621,0.00003457145,0.0001382841,0.001116144,0.001284939],"genre_scores_gemma":[0.7388414,0.0004956452,0.2534772,0.0003905709,0.0002084463,0.0001938713,0.001134264,0.0004128159,0.004845892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002654542,"threshold_uncertainty_score":0.01403868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01884537171818267,"score_gpt":0.2462396019807343,"score_spread":0.2273942302625516,"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."}}