{"id":"W2115328154","doi":"10.1109/icassp.2004.1325916","title":"Disentangling speaker and channel effects in speaker verification","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker recognition; Speaker diarisation; NIST; Computer science; Speaker verification; Speech recognition; Variation (astronomy); Task (project management); Channel (broadcasting); Factor (programming language); Construct (python library); Joint (building); Artificial intelligence; Telecommunications; Engineering","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":[0.0001087729,0.00006521307,0.00007315282,0.00008545097,0.00003147282,0.00007033983,0.0001135591,0.0000284315,0.00001176574],"category_scores_gemma":[0.00003635713,0.00005694278,0.00001827471,0.000183896,0.00001533098,0.0002493585,0.00003719224,0.00004197915,0.0001024703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002944495,"about_ca_system_score_gemma":0.00001124967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002951295,"about_ca_topic_score_gemma":0.00005472009,"domain_scores_codex":[0.9994563,0.00001992864,0.00009545634,0.0002096671,0.00009522189,0.0001234649],"domain_scores_gemma":[0.999716,0.0000458234,0.00001964132,0.0001554945,0.00001032699,0.00005266712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002399811,0.0005502065,0.0162093,0.00009119749,0.00003067553,0.0002283387,0.004423535,0.0001090643,0.005731304,0.1750139,0.0002545981,0.7973338],"study_design_scores_gemma":[0.006305002,0.0002175415,0.4831618,0.0004571094,0.00002409951,0.000222945,0.0006493008,0.1328942,0.2214641,0.1504445,0.002684401,0.001474934],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5474977,0.0001047528,0.4346426,0.002224016,0.0003117848,0.0002553967,3.847146e-7,0.0001784316,0.01478491],"genre_scores_gemma":[0.9658953,0.00002124485,0.03352708,0.0004205756,0.00002299895,0.000009104547,8.457862e-7,0.00000405893,0.00009882227],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7958589,"threshold_uncertainty_score":0.2322059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01152059726138061,"score_gpt":0.2197334941465341,"score_spread":0.2082128968851535,"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."}}