{"id":"W2292259253","doi":"10.1109/asru.2015.7404844","title":"Deep bottleneck features for i-vector based text-independent speaker verification","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Speaker verification; NIST; Computer science; Speech recognition; Discriminative model; Bottleneck; Speaker recognition; Cepstrum; Mel-frequency cepstrum; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Feature extraction","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":[0.001267132,0.0007317749,0.0006751115,0.0006480628,0.0003563892,0.0005284079,0.0009143588,0.0005209951,0.003678011],"category_scores_gemma":[0.002402279,0.0002639189,0.0003862398,0.0003998551,0.0002560474,0.001169074,0.0009743997,0.001061762,0.001462592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005591329,"about_ca_system_score_gemma":0.0008440868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002735649,"about_ca_topic_score_gemma":0.004404826,"domain_scores_codex":[0.9995198,0.00008982847,0.00003240883,0.0001043765,0.0001904778,0.00006308318],"domain_scores_gemma":[0.9992179,0.0003084004,0.00008475076,0.0001200833,0.0002347641,0.00003421432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001040284,0.0002112613,0.001917947,0.0001789428,0.00006466227,0.0001426295,0.0001039889,0.06552856,0.1679276,0.004064419,0.004211087,0.7546087],"study_design_scores_gemma":[0.00002246256,0.0002717394,0.002786578,0.00002784899,0.00004177444,0.0001519562,0.00003397226,0.8877248,0.1016986,0.003093272,0.004108651,0.00003844517],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.100556,0.001386316,0.8894744,0.0001905257,0.0001282153,0.000111524,0.0006866432,0.004463135,0.003003223],"genre_scores_gemma":[0.7070033,0.0004633944,0.2850507,0.0001067088,0.0000644852,0.0001477754,0.00207323,0.0001948601,0.004895543],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003678011,"threshold_uncertainty_score":0.01230419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04303567032976717,"score_gpt":0.2653664152367965,"score_spread":0.2223307449070294,"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."}}