{"id":"W2001936727","doi":"10.1109/lsp.2007.905088","title":"Combining Gaussianized/Non-Gaussianized Features to Improve Speaker Diarization of Telephone Conversations","year":2007,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Speaker diarisation; Viterbi algorithm; Computer science; Cluster analysis; Speech recognition; Mixture model; Pattern recognition (psychology); Segmentation; Bayesian information criterion; Mel-frequency cepstrum; Feature (linguistics); Artificial intelligence; Speaker recognition; Word error rate; Test set; Hierarchical clustering; Feature extraction; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002571338,0.001683283,0.001381392,0.001438452,0.0005034486,0.0008683114,0.0007453482,0.0007778113,0.002796448],"category_scores_gemma":[0.003909823,0.0003550288,0.001256985,0.001090326,0.0003216045,0.001161407,0.001063101,0.000963149,0.002641727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003748898,"about_ca_system_score_gemma":0.0005937288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004744414,"about_ca_topic_score_gemma":0.006671484,"domain_scores_codex":[0.9982259,0.000404059,0.00008204378,0.0005288808,0.0004742372,0.0002850058],"domain_scores_gemma":[0.9977894,0.0008204498,0.00008715813,0.0003185443,0.000881544,0.0001029568],"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":[0.001577861,0.0004636273,0.003989101,0.0002279451,0.0003140681,0.0001991659,0.0002724604,0.02535516,0.1195864,0.000465259,0.004516109,0.8430328],"study_design_scores_gemma":[0.0003510695,0.001530138,0.03532565,0.00003822844,0.0008766636,0.0009208083,0.0003017982,0.5734382,0.3676856,0.001471791,0.0177698,0.0002901788],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4210048,0.001857835,0.5563313,0.0004148302,0.0005280871,0.000250518,0.001128391,0.01279938,0.005684873],"genre_scores_gemma":[0.5103622,0.0005093376,0.475665,0.0002077215,0.0001660173,0.0001196934,0.004601572,0.001086178,0.007282367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004744414,"threshold_uncertainty_score":0.01359874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01048864228849473,"score_gpt":0.2396504136676137,"score_spread":0.229161771379119,"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."}}