{"id":"W1981185131","doi":"10.1109/iscslp.2014.6936584","title":"Speaker adaptive bottleneck features extraction for LVCSR based on discriminative learning of speaker codes","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speech recognition; Discriminative model; Speaker recognition; Hidden Markov model; Bottleneck; Speaker diarisation; Adaptation (eye); Word error rate; Pattern recognition (psychology); Feature extraction; Artificial intelligence; Task (project management); Engineering","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":[0.0007058534,0.0008859767,0.0007827746,0.001193283,0.0002295859,0.0002897915,0.000754121,0.000451853,0.001666094],"category_scores_gemma":[0.001162364,0.0003035056,0.000523351,0.0007038524,0.0002864043,0.0006771206,0.0005641317,0.0008050101,0.001071049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003504129,"about_ca_system_score_gemma":0.0005958689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002235803,"about_ca_topic_score_gemma":0.003817051,"domain_scores_codex":[0.9995926,0.00007869166,0.00002434346,0.0001034682,0.00016116,0.00003986637],"domain_scores_gemma":[0.9994007,0.0002228651,0.00004486208,0.00008499049,0.0002167689,0.00002973999],"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":[0.0003087712,0.0001116415,0.001295088,0.0001614331,0.00007443112,0.000114382,0.00008814443,0.02064836,0.2453285,0.00154263,0.002331695,0.7279949],"study_design_scores_gemma":[0.00003267092,0.000181063,0.005863012,0.00002176153,0.00007258377,0.0003131431,0.00003620603,0.8346443,0.1522575,0.001509007,0.005007958,0.00006083729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0220405,0.0005774953,0.9750906,0.00004505641,0.00003699981,0.00005851879,0.0001335975,0.00147238,0.000544911],"genre_scores_gemma":[0.307201,0.0006669771,0.6874961,0.000102225,0.00009088388,0.0002417143,0.001408157,0.0002942232,0.002498704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002235803,"threshold_uncertainty_score":0.00557363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02734363352919382,"score_gpt":0.2756229960611707,"score_spread":0.2482793625319769,"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."}}