{"id":"W3200111860","doi":"10.1007/978-3-030-87802-3_1","title":"Text-Independent Speaker Verification Employing CNN-LSTM-TDNN Hybrid Networks","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Speech recognition; NIST; Artificial neural network; Time delay neural network; Speaker recognition; Artificial intelligence; Pattern recognition (psychology); Utterance; Pooling; Convolutional neural network","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001075093,0.000628653,0.0006295698,0.0007429136,0.0003831407,0.001258906,0.00299229,0.0003523204,0.0002518253],"category_scores_gemma":[0.0001677947,0.0006206222,0.000250478,0.0007043802,0.0003966629,0.0007117553,0.001165944,0.001052936,0.000207954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004223255,"about_ca_system_score_gemma":0.0005485383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002173269,"about_ca_topic_score_gemma":0.00006348878,"domain_scores_codex":[0.9948795,0.00008523308,0.0007118948,0.002149998,0.001351245,0.0008220586],"domain_scores_gemma":[0.9965207,0.0005709992,0.0003761151,0.001843639,0.0004118393,0.0002767273],"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":[0.000003769544,0.00003822729,0.00004777128,0.00001739506,0.00001892873,0.0002529488,0.0001426018,0.009033263,0.0001104414,0.006198794,0.00008203068,0.9840539],"study_design_scores_gemma":[0.0003656928,0.00009287488,0.0004823652,0.0006994362,0.00002437919,0.0005191221,6.568187e-7,0.944918,0.004660734,0.03892263,0.007948338,0.001365781],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001294501,0.0005862677,0.9880734,0.0008424201,0.003023485,0.0003580427,0.000004674845,0.000264183,0.006718074],"genre_scores_gemma":[0.2354346,0.0004440437,0.7540051,0.005923229,0.001722873,0.00004147376,0.00005330967,0.0001321496,0.002243195],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9826881,"threshold_uncertainty_score":0.9997779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02357076226519661,"score_gpt":0.2391657481355195,"score_spread":0.2155949858703229,"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."}}