{"id":"W2015633636","doi":"10.1109/icassp.2014.6854823","title":"I-vector-based speaker adaptation of deep neural networks for French broadcast audio transcription","year":2014,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":119,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speech recognition; Computer science; Speaker diarisation; Word error rate; Transcription (linguistics); Feature vector; Hidden Markov model; Artificial neural network; Artificial intelligence; Speaker recognition; Acoustic model; Vector quantization; Pattern recognition (psychology); Speech processing","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":[0.0002520087,0.00009968226,0.0001429147,0.00008353911,0.00005878402,0.00005278408,0.0002339065,0.00006089713,0.0001284209],"category_scores_gemma":[0.0000481758,0.0000881977,0.0001230344,0.0001844641,0.0000242183,0.0002248338,0.000008619801,0.00004630386,0.000009342182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001465372,"about_ca_system_score_gemma":0.00001130377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005850014,"about_ca_topic_score_gemma":0.0001569336,"domain_scores_codex":[0.9991374,0.00007179943,0.0002287783,0.0002268275,0.0001614603,0.0001737585],"domain_scores_gemma":[0.9993014,0.0001977018,0.00008214496,0.0002210581,0.0001370624,0.00006064656],"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":[0.00001281474,0.00006085529,0.0001209168,0.00001545841,0.000008712835,2.89597e-7,0.0001403727,0.01018468,0.001667193,0.004777859,0.0002296559,0.9827812],"study_design_scores_gemma":[0.0004883284,0.0001246851,0.003014132,0.000006871755,0.000009959331,0.000001761714,0.00001784527,0.9906013,0.004143672,0.0003565682,0.001123875,0.0001110068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007863239,0.00002613584,0.9896209,0.0004235755,0.0003545502,0.0001907742,0.000001600768,0.0001062629,0.001412936],"genre_scores_gemma":[0.8271446,0.000001098606,0.1723234,0.0003408456,0.00007584228,0.00002107599,0.000009558611,0.000006346655,0.00007729334],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9826702,"threshold_uncertainty_score":0.3596598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02772913931601576,"score_gpt":0.2293340230087177,"score_spread":0.2016048836927019,"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."}}