{"id":"W1849358290","doi":"","title":"Segmentation into audio document speakers: A new approach based on the one- class support vector methods","year":2007,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Speaker diarisation; Computer science; Speech recognition; Search engine indexing; Audio mining; Class (philosophy); Speaker recognition; Support vector machine; Cluster analysis; Process (computing); Metric (unit); Information retrieval; Voice activity detection; Artificial intelligence; Speech processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001299334,0.001391404,0.001561501,0.003352889,0.000456649,0.001910444,0.002232218,0.001556353,0.001615784],"category_scores_gemma":[0.002902574,0.0004838301,0.001332644,0.002086003,0.0006799774,0.001993045,0.0009116664,0.001998603,0.001445699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005199368,"about_ca_system_score_gemma":0.0008351718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003034103,"about_ca_topic_score_gemma":0.00183533,"domain_scores_codex":[0.9978076,0.0003481972,0.0001889029,0.0007185049,0.0007956242,0.0001412659],"domain_scores_gemma":[0.9985048,0.0005032389,0.0001657994,0.0001090997,0.000639067,0.0000779963],"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":[0.0001906763,0.0001599768,0.001191525,0.0002596887,0.0001136881,0.000106703,0.000168588,0.02876548,0.01850913,0.004691095,0.003549553,0.9422938],"study_design_scores_gemma":[0.00001928046,0.0001966292,0.00177926,0.00005644664,0.00005167776,0.0002180788,0.0001054389,0.9763381,0.008026803,0.005132788,0.008015485,0.00005999495],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004498285,0.0007625007,0.9930713,0.0001016474,0.0001265761,0.00006873811,0.00007385918,0.0007203122,0.0005767933],"genre_scores_gemma":[0.1354676,0.001460411,0.8570556,0.0001787318,0.0005478366,0.0002746231,0.0007983989,0.0002899308,0.003926974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003352889,"threshold_uncertainty_score":0.006871641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03267067337298706,"score_gpt":0.3050593848598383,"score_spread":0.2723887114868512,"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."}}