{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002286218,0.00009871102,0.0001125992,0.00004833139,0.0001079984,0.0001464795,0.00020479,0.00003562784,0.0001430385],"category_scores_gemma":[0.00006567135,0.0000747673,0.00005065127,0.0002910595,0.00001930907,0.0004453657,0.00002492494,0.00003151665,0.00004078296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001110692,"about_ca_system_score_gemma":0.000009108044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001079702,"about_ca_topic_score_gemma":0.0001120807,"domain_scores_codex":[0.9991005,0.00006445253,0.0001667521,0.0002783463,0.0001731028,0.0002168168],"domain_scores_gemma":[0.9993047,0.0001645364,0.00007002168,0.0002718444,0.0001204741,0.00006847919],"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":[0.0001006667,0.00008625825,0.004810705,0.0000201545,0.00004466331,0.00000457735,0.0005818676,0.01178089,0.0002350703,0.1031214,0.007647502,0.8715662],"study_design_scores_gemma":[0.0005758058,0.00009726908,0.006970744,0.000005787992,0.00001005042,0.00001771258,0.00002700549,0.9834781,0.001317612,0.002802909,0.004542117,0.0001548562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003613063,0.000004228094,0.9764566,0.001056338,0.0001945887,0.0002522354,3.194999e-7,0.0001845641,0.01823804],"genre_scores_gemma":[0.5293452,0.000001978729,0.4669928,0.002074311,0.0003744613,0.00004736583,0.00002396741,0.00001545746,0.001124501],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9716972,"threshold_uncertainty_score":0.3048922,"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."}}