{"id":"W2084215616","doi":"10.1109/icassp.2014.6854821","title":"Two-stage speaker adaptation in subspace Gaussian mixture models","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Subspace topology; Feature vector; Hidden Markov model; Pattern recognition (psychology); Context (archaeology); Mixture model; Artificial intelligence; Projection (relational algebra); Linear subspace; Feature (linguistics); Covariance; Gaussian; Adaptation (eye); 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":[0.0002935192,0.00009188592,0.0001051204,0.0001242058,0.00003456389,0.0001024806,0.0002834448,0.00004627456,0.0002041881],"category_scores_gemma":[0.00003341872,0.00007738729,0.00003861606,0.0002632066,0.00001288637,0.0005074621,0.00004383793,0.00008048392,0.0002155496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002229615,"about_ca_system_score_gemma":0.0000203166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001578216,"about_ca_topic_score_gemma":0.001002654,"domain_scores_codex":[0.9991384,0.00009004774,0.0001379555,0.0002673192,0.0001833487,0.0001828923],"domain_scores_gemma":[0.9994743,0.00007696502,0.00003758763,0.0003055028,0.00003299084,0.00007263002],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006677055,0.00007800763,0.0002095302,0.000008505958,0.000005943774,0.00001502213,0.001463663,0.002617475,0.0006461974,0.7435004,0.0009144678,0.2505341],"study_design_scores_gemma":[0.0003083033,0.00001391293,0.0007237676,0.0000110487,0.000001177195,0.000004110976,0.0001421663,0.9770089,0.002763285,0.01620585,0.002679529,0.0001379156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00580944,0.000009222003,0.8233232,0.001608643,0.00009658656,0.00007148355,5.461061e-7,0.0001132964,0.1689675],"genre_scores_gemma":[0.7591478,0.000004805365,0.2361252,0.0008584099,0.000032383,0.000006736926,0.000001617015,0.00000576547,0.003817226],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9743915,"threshold_uncertainty_score":0.3155762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03397410928857877,"score_gpt":0.2480830844242725,"score_spread":0.2141089751356937,"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."}}