{"id":"W2055696218","doi":"10.1109/odyssey.2006.248137","title":"The Geometry of the Channel Space in GMM-Based Speaker Recognition","year":2006,"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":"Channel (broadcasting); Mixture model; Joint (building); Range (aeronautics); Rank (graph theory); Pattern recognition (psychology); Computer science; Gaussian; Factor (programming language); Artificial intelligence; Feature (linguistics); Factor analysis; Feature vector; Space (punctuation); Limiting; Mathematics; Machine learning; Combinatorics; Telecommunications; Physics; Engineering","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":[0.0004020892,0.00007116733,0.00007851132,0.00008885685,0.00008829818,0.00005960093,0.0004457878,0.00003922111,0.00007551644],"category_scores_gemma":[0.0000929976,0.00003816747,0.00007403926,0.0006569094,0.00005443039,0.0001033397,0.00005927664,0.00007587527,0.00007560474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002169321,"about_ca_system_score_gemma":0.0000349957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000240321,"about_ca_topic_score_gemma":0.0005333639,"domain_scores_codex":[0.9991891,0.00009208185,0.0001829098,0.0001533521,0.000220343,0.0001622044],"domain_scores_gemma":[0.9991977,0.0002965006,0.00007606753,0.0003451329,0.00006618592,0.00001846279],"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":[0.00006392171,0.001033884,0.01142504,0.00005747925,0.00003817898,0.00002282514,0.0003300108,0.0003671888,0.006487054,0.05151366,0.03045844,0.8982023],"study_design_scores_gemma":[0.001475004,0.00007482988,0.2263683,0.0001515709,0.00001412897,0.00001880484,0.0002834573,0.09852088,0.5872496,0.07353759,0.01179095,0.000514892],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5440282,0.0002030734,0.2282477,0.03384898,0.001292957,0.0007778878,0.00001233533,0.0002395317,0.1913494],"genre_scores_gemma":[0.9906201,0.000007128381,0.007486757,0.0005350698,0.00004248596,0.00001291578,0.000001238918,0.000005114359,0.001289185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8976874,"threshold_uncertainty_score":0.1556424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01565638295550802,"score_gpt":0.2045470112893858,"score_spread":0.1888906283338778,"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."}}