{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002072989,0.0002735027,0.0003169618,0.0003494945,0.0006927728,0.0001730975,0.001073222,0.0001764141,0.00003194066],"category_scores_gemma":[0.0003052244,0.0003062454,0.0001235294,0.0008517183,0.00008660413,0.0005046778,0.0001683873,0.0004579517,0.00001026991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003078996,"about_ca_system_score_gemma":0.0005912937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007158946,"about_ca_topic_score_gemma":0.0004058694,"domain_scores_codex":[0.9974248,0.0005231561,0.0005630077,0.0005432533,0.0001764125,0.0007693307],"domain_scores_gemma":[0.9973914,0.0004811202,0.0002018324,0.001555479,0.0002577977,0.0001123826],"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":[0.00001868602,0.0003797791,0.00005812029,0.00001608697,0.00003694982,1.956501e-7,0.0002097229,0.0001476578,0.001510215,0.3753526,0.0003406765,0.6219293],"study_design_scores_gemma":[0.0008971748,0.000276544,0.00001516711,0.00003122675,0.000034436,0.00002726084,0.00003147156,0.6930822,0.02576154,0.1353213,0.1440888,0.0004328895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01274336,0.007985932,0.9682823,0.002446082,0.00009522876,0.0009257195,0.0000119162,0.0002059651,0.007303522],"genre_scores_gemma":[0.14906,0.005652294,0.8433055,0.0009207484,0.00002059189,0.0005284969,0.0001486612,0.00004377037,0.0003199718],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6929345,"threshold_uncertainty_score":0.999939,"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."}}