{"id":"W2067459736","doi":"10.1002/ecjb.10119","title":"Model‐based speaker normalization methods for speech recognition","year":2003,"lang":"en","type":"article","venue":"Electronics and Communications in Japan (Part II Electronics)","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Vocal tract; Formant; Normalization (sociology); Speech recognition; Computer science; Speaker recognition; Smoothing; Speaker diarisation; Image warping; Pattern recognition (psychology); Artificial intelligence; Computer vision","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":[0.001200741,0.0008764463,0.000950336,0.0007665023,0.0003515562,0.0006423408,0.001062258,0.0007002339,0.003775372],"category_scores_gemma":[0.00207061,0.0004747106,0.00088825,0.0005694363,0.0003925841,0.0007673473,0.0005986108,0.0009296773,0.003054954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004933646,"about_ca_system_score_gemma":0.0005298496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001662057,"about_ca_topic_score_gemma":0.001881244,"domain_scores_codex":[0.9990309,0.0003032717,0.00004260015,0.0002098095,0.0003691129,0.00004428752],"domain_scores_gemma":[0.999416,0.0002223081,0.00004721545,0.000103992,0.0001978902,0.00001269878],"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":[0.0001990759,0.00007081083,0.0003160064,0.0002098252,0.00016797,0.00008460751,0.00009269622,0.0921498,0.06076185,0.008220769,0.004998715,0.8327277],"study_design_scores_gemma":[0.00002138972,0.00005057457,0.0005991765,0.00001860032,0.00004748396,0.0001702411,0.00001691995,0.9525243,0.03261311,0.004983728,0.00891558,0.00003884942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001572311,0.0003347811,0.9960962,0.00003215663,0.00004045649,0.00002691639,0.00003327251,0.001460719,0.0004032144],"genre_scores_gemma":[0.1004132,0.000827878,0.8919452,0.00009849457,0.0001230688,0.0003803096,0.0004792731,0.0004882631,0.005244489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003775372,"threshold_uncertainty_score":0.01262981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06666757292295987,"score_gpt":0.3387917852170029,"score_spread":0.272124212294043,"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."}}