{"id":"W1998280908","doi":"10.1109/asru.2007.4430198","title":"Multiple feature combination to improve speaker diarization of telephone conversations","year":2007,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker diarisation; Viterbi algorithm; Computer science; Mixture model; Cluster analysis; Speech recognition; Pattern recognition (psychology); Segmentation; Feature (linguistics); Bayesian information criterion; Artificial intelligence; Hierarchical clustering; Test set; Speaker recognition; Word error rate; Hidden Markov model","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":[0.0002798503,0.000064224,0.00008418051,0.0001693692,0.00004687353,0.00003465854,0.0001835911,0.00005514318,0.00008414285],"category_scores_gemma":[0.0002192366,0.0000592463,0.00003594883,0.0004782557,0.0000149576,0.0002451081,0.00004629745,0.00004371727,0.0001045316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003032906,"about_ca_system_score_gemma":0.00002065861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003882801,"about_ca_topic_score_gemma":0.00008655152,"domain_scores_codex":[0.9993436,0.00001541624,0.0001545116,0.0001718793,0.0001912606,0.0001232772],"domain_scores_gemma":[0.9992833,0.0001602017,0.00006138532,0.0002120189,0.0002075214,0.0000755931],"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":[0.00002826808,0.0004311282,0.009628013,0.00002038242,0.00003569154,0.000004302059,0.00172066,0.00001285848,0.308401,0.05287322,0.006777423,0.620067],"study_design_scores_gemma":[0.0006277868,0.00007774377,0.0681055,0.000009834393,0.000005752097,0.000003174257,0.0001623402,0.01815293,0.9082782,0.001065587,0.003350146,0.0001610589],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04235546,0.000003138249,0.9466261,0.001485009,0.0002706812,0.0002140169,0.000003460923,0.00009600241,0.008946178],"genre_scores_gemma":[0.8653333,0.000001454058,0.1331161,0.0004880406,0.00002177556,0.000004294882,0.000008008581,0.00000402661,0.001022982],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8229778,"threshold_uncertainty_score":0.2415994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01019034914074989,"score_gpt":0.2296411357601296,"score_spread":0.2194507866193797,"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."}}