{"id":"W2055842011","doi":"10.1109/icassp.2014.6854822","title":"Deep neural network trained with speaker representation for speaker normalization","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Normalization (sociology); Speech recognition; Computer science; Discriminative model; Speaker recognition; Pattern recognition (psychology); Feature extraction; Word error rate; Artificial neural network; Artificial intelligence; Speaker diarisation","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":[0.000468275,0.0004543088,0.0003635161,0.0002176787,0.0002513868,0.0003503733,0.0006153149,0.0005287547,0.002097861],"category_scores_gemma":[0.0007453351,0.0002572948,0.0003224642,0.0002831341,0.0002055254,0.0005807694,0.0005651437,0.001159925,0.0009045303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005674441,"about_ca_system_score_gemma":0.00060634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004104316,"about_ca_topic_score_gemma":0.00884912,"domain_scores_codex":[0.9997761,0.00003869536,0.00001036451,0.00007357206,0.00007278693,0.00002844533],"domain_scores_gemma":[0.9998599,0.00003873959,0.00001222637,0.00002581622,0.00005529855,0.000007879722],"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":[0.0002668066,0.0001179027,0.0008803497,0.0001037552,0.0001215136,0.0001120369,0.00008864792,0.1491996,0.140607,0.008031055,0.005820691,0.6946507],"study_design_scores_gemma":[0.000008280792,0.0000479333,0.0004990336,0.000007929192,0.0000260892,0.00006806006,0.000008001868,0.9663228,0.02779862,0.001481613,0.003719113,0.00001250212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02125194,0.0004289433,0.9729608,0.0001234365,0.00012252,0.00003478951,0.0001384085,0.001963292,0.002976025],"genre_scores_gemma":[0.450264,0.0004478249,0.530647,0.0002711618,0.00008260987,0.0001622508,0.0007841271,0.0001861378,0.01715492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004104316,"threshold_uncertainty_score":0.00816083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02168773414574742,"score_gpt":0.2424845208748048,"score_spread":0.2207967867290574,"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."}}