{"id":"W2121415728","doi":"10.1109/tsa.2004.840940","title":"Eigenvoice modeling with sparse training data","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":472,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; Training set; Set (abstract data type); Adaptation (eye); Limit (mathematics); Training (meteorology); Maximum likelihood; Covariance matrix; Pattern recognition (psychology); Estimation theory; Artificial intelligence; Covariance; Speaker recognition; Algorithm; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002726736,0.0001901879,0.0001879965,0.0001690448,0.0004653042,0.0003546628,0.0005125126,0.00006532085,0.00003195935],"category_scores_gemma":[0.000005599377,0.0001617532,0.00003005645,0.0003566868,0.00004804187,0.001550951,0.000005577777,0.0002392281,0.00003861698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002682919,"about_ca_system_score_gemma":0.0001330814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001081001,"about_ca_topic_score_gemma":0.00008380025,"domain_scores_codex":[0.9985489,0.00002995086,0.0002185233,0.0005894941,0.0002953285,0.0003178173],"domain_scores_gemma":[0.9991725,0.00005118871,0.00006399122,0.0004880103,0.00007161476,0.0001526927],"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":[0.00001484614,0.00006165026,0.000001055254,0.00001537318,0.00001530759,0.00001178199,0.0006581083,0.00325511,0.0004572441,0.00001467323,0.00001197543,0.9954829],"study_design_scores_gemma":[0.0004644322,0.00005592065,0.000004579971,0.0001738202,0.00003448621,0.0002031499,0.0003166973,0.9686379,0.02806155,0.0001262747,0.001602705,0.0003185304],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01749291,0.0001897205,0.9787946,0.001346009,0.00007415235,0.000100906,0.00001016485,0.0002581822,0.00173341],"genre_scores_gemma":[0.6683116,0.00008420311,0.3307822,0.0005898212,0.00007045313,0.000008308363,0.000001620514,0.00001475465,0.0001370415],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9951643,"threshold_uncertainty_score":0.6596104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.095794255220844,"score_gpt":0.2797844726229301,"score_spread":0.1839902174020861,"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."}}