{"id":"W2096875330","doi":"10.1109/tasl.2008.916530","title":"Rapid Speaker Adaptation Using Clustered Maximum-Likelihood Linear Basis With Sparse Training Data","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Basis (linear algebra); Adaptation (eye); Computer science; Maximum likelihood; Pattern recognition (psychology); Speech recognition; Artificial intelligence; Statistics; Mathematics; Psychology","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":[0.0007760337,0.0005231904,0.0004965244,0.0003843194,0.0002426952,0.0002919955,0.0007234353,0.0005554524,0.00107209],"category_scores_gemma":[0.002695857,0.0004171215,0.0004864872,0.0005914887,0.0002945758,0.0006053526,0.0007486124,0.0009849238,0.0006904497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001987876,"about_ca_system_score_gemma":0.0004350992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002326576,"about_ca_topic_score_gemma":0.003586839,"domain_scores_codex":[0.9995059,0.0002106603,0.00001883982,0.00008530599,0.0001478473,0.00003147016],"domain_scores_gemma":[0.9989029,0.0006849489,0.00007228947,0.0001450766,0.0001676658,0.00002704443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004657047,0.0002236087,0.0007050917,0.0001074227,0.0001408946,0.0001105162,0.0002212362,0.2700647,0.100097,0.005450068,0.00297215,0.6194415],"study_design_scores_gemma":[0.00001898231,0.00005975444,0.0003783634,0.00000383242,0.000009736344,0.0000468742,0.00001105973,0.985298,0.01232559,0.0009784804,0.0008523628,0.00001693614],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01246135,0.0000930593,0.9862375,0.00003545115,0.00001922838,0.00002920939,0.00002001241,0.0007836925,0.0003205188],"genre_scores_gemma":[0.2091396,0.000140614,0.7881446,0.00006992408,0.00004708273,0.0001696656,0.0003287053,0.0001621597,0.001797551],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002326576,"threshold_uncertainty_score":0.004626036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09851490030450993,"score_gpt":0.2764646673115335,"score_spread":0.1779497670070236,"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."}}