{"id":"W2165712617","doi":"10.1109/tasl.2007.914114","title":"Capturing Local Variability for Speaker Normalization in Speech Recognition","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":"Hidden Markov model; Normalization (sociology); Image warping; Speech recognition; Computer science; Dynamic time warping; Artificial intelligence; Pattern recognition (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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005402738,0.0001882941,0.0002122076,0.000279741,0.0003106316,0.0001020049,0.000161192,0.0001236319,0.00007518545],"category_scores_gemma":[0.00004399965,0.0001870708,0.0000743982,0.0004578833,0.00007745284,0.000743008,0.000002832083,0.0002027056,0.00002126614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009333561,"about_ca_system_score_gemma":0.00008440715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009158885,"about_ca_topic_score_gemma":0.0002028174,"domain_scores_codex":[0.9985819,0.00009518374,0.0003165456,0.0004755821,0.0002218339,0.0003089027],"domain_scores_gemma":[0.9993268,0.0001670273,0.00008553981,0.000203138,0.0001116702,0.0001058369],"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":[0.00003890299,0.0001457522,0.00004180781,0.00007874354,0.00000728381,0.00005086334,0.001543464,0.00007323622,0.0011922,0.000005112658,0.00001425337,0.9968084],"study_design_scores_gemma":[0.002462805,0.0001797655,0.001114949,0.0003893345,0.00004900083,0.001088633,0.001139615,0.2354123,0.7553939,0.001567379,0.0002928518,0.0009095072],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1138516,0.00009138033,0.8844373,0.0002198698,0.0001536035,0.0003011024,0.00001355157,0.0001749711,0.0007566515],"genre_scores_gemma":[0.870535,0.00005042997,0.1287979,0.0003421571,0.0000497996,0.00005485062,0.000006610913,0.00001677857,0.0001465682],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9958989,"threshold_uncertainty_score":0.7628526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02366902432876057,"score_gpt":0.2478770694418866,"score_spread":0.2242080451131261,"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."}}