{"id":"W2586956420","doi":"10.1109/slt.2016.7846264","title":"Modelling speaker and channel variability using deep neural networks for robust speaker verification","year":2016,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Computer Research Institute of Montréal","funders":"Nvidia","keywords":"Speaker verification; Computer science; Normalization (sociology); Word error rate; Speech recognition; Speaker recognition; Classifier (UML); Pattern recognition (psychology); Artificial neural network; Artificial intelligence; Discrete cosine transform; Deep neural networks","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":[0.001146251,0.0007005389,0.0005018105,0.0003406738,0.0002272019,0.0006158773,0.0007813814,0.0005289216,0.001366419],"category_scores_gemma":[0.00252355,0.0003621543,0.0005510288,0.00028248,0.0003671108,0.001113478,0.0008146333,0.00155464,0.000519366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005462218,"about_ca_system_score_gemma":0.0008082299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005307083,"about_ca_topic_score_gemma":0.008337209,"domain_scores_codex":[0.9995348,0.00011306,0.00002158123,0.0001315111,0.0001364173,0.00006257952],"domain_scores_gemma":[0.9993222,0.0003435499,0.0000937595,0.00009468161,0.0001235954,0.00002230912],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004100191,0.0001016581,0.003781073,0.00007576941,0.0001308091,0.0001009962,0.00009888728,0.6082783,0.05083487,0.004467485,0.001362746,0.3303573],"study_design_scores_gemma":[0.000002652255,0.00001551792,0.0004112705,0.000003393496,0.000007679811,0.0000209851,0.000003985951,0.9925483,0.005645885,0.001062141,0.0002719511,0.000006259901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05184769,0.0003103023,0.9453151,0.000156396,0.00005928258,0.00002021059,0.0001113739,0.0008262784,0.001353386],"genre_scores_gemma":[0.8393699,0.000269938,0.1562226,0.0001145402,0.0000546158,0.00004928357,0.0003458025,0.0001508346,0.003422581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005307083,"threshold_uncertainty_score":0.01055235,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07338699910887467,"score_gpt":0.2456055521845424,"score_spread":0.1722185530756677,"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."}}