{"id":"W2163786726","doi":"10.1007/s11265-015-1012-6","title":"Speaker Adaptation of Hybrid NN/HMM Model for Speech Recognition Based on Singular Value Decomposition","year":2015,"lang":"en","type":"article","venue":"Journal of Signal Processing Systems","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Speech recognition; Singular value decomposition; TIMIT; Hidden Markov model; Adaptation (eye); Vocabulary; Speaker recognition; Pattern recognition (psychology); Artificial intelligence; Artificial neural network; Task (project management)","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":[0.0003796903,0.0003962899,0.0005957439,0.0002498154,0.0002349908,0.000325474,0.0004637911,0.0004565084,0.001754523],"category_scores_gemma":[0.0005862226,0.0002390027,0.0006575696,0.0002855563,0.0001204418,0.0004125532,0.0002842078,0.000624058,0.001327657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001573161,"about_ca_system_score_gemma":0.0003235019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003930071,"about_ca_topic_score_gemma":0.004849232,"domain_scores_codex":[0.9997438,0.00006089202,0.00001616358,0.00007953049,0.00007725869,0.00002241622],"domain_scores_gemma":[0.9997839,0.00006602416,0.000009268396,0.00002948874,0.000101074,0.0000102032],"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":[0.0005783412,0.0001642369,0.002399316,0.0001856016,0.0002255799,0.0002040576,0.0001575715,0.1749005,0.1978183,0.002207711,0.003469903,0.6176889],"study_design_scores_gemma":[0.000005631265,0.00004652831,0.001515361,0.000007060078,0.00003705798,0.0001014968,0.00001056845,0.9800832,0.0165108,0.0003931045,0.001273886,0.00001526253],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02934953,0.0004709781,0.9677425,0.00005300778,0.0001213604,0.00002035156,0.00008702793,0.001013994,0.001141215],"genre_scores_gemma":[0.6631777,0.0007867978,0.3270794,0.00009677441,0.0001007879,0.0001127288,0.0007874441,0.000278391,0.007579882],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003930071,"threshold_uncertainty_score":0.007814348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08558740047888537,"score_gpt":0.293905759405991,"score_spread":0.2083183589271057,"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."}}