{"id":"W1597208282","doi":"10.1109/icassp.2015.7178806","title":"Speaker change point detection using deep neural nets","year":2015,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker diarisation; Change detection; Computer science; Speech recognition; Frame (networking); Artificial neural network; Point (geometry); Set (abstract data type); Speaker recognition; Test set; Speech processing; Word error rate; Voice activity detection; Artificial intelligence; Mathematics; Telecommunications","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":[0.0001637988,0.00007193141,0.00007096596,0.00008182132,0.00004701376,0.0001072559,0.0001767973,0.00003427313,0.00009179649],"category_scores_gemma":[0.0000373092,0.00006080986,0.00003789035,0.0001968258,0.00001129893,0.0005770597,0.00007795575,0.00004648437,0.000242102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004190662,"about_ca_system_score_gemma":0.000009307564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001527019,"about_ca_topic_score_gemma":0.0001263696,"domain_scores_codex":[0.9993509,0.0000448496,0.00009755156,0.0001802082,0.0001666626,0.0001598339],"domain_scores_gemma":[0.9995818,0.00001875617,0.00003122237,0.0001946963,0.00007241958,0.0001011642],"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":[0.000003439883,0.00002247496,0.000161135,0.000001323431,0.000004066323,0.00001674711,0.0004059933,0.000006717212,0.0008604237,0.0004283595,0.00009211731,0.9979972],"study_design_scores_gemma":[0.0002155193,0.0000458017,0.002128954,0.000003582464,0.000003771348,0.0001527139,0.0001026932,0.9753251,0.01845462,0.001505032,0.001907877,0.0001543556],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1716395,0.00003867111,0.8167099,0.0009791023,0.000879364,0.0001219169,2.162565e-7,0.0002758981,0.00935535],"genre_scores_gemma":[0.9410715,0.000001094028,0.0570792,0.001599534,0.0001402523,0.000005624316,2.888525e-7,0.000005527673,0.00009699375],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9978428,"threshold_uncertainty_score":0.3111812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1755712714818029,"score_gpt":0.2864213862817155,"score_spread":0.1108501147999126,"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."}}