{"id":"W2539873419","doi":"10.1109/icscs.2009.5412479","title":"Comparison of GMM and fuzzy-GMM applied to phoneme classification","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Keyword spotting; Speech recognition; Utterance; Classifier (UML); Vocabulary; Artificial intelligence; Mixture model; Spotting; Natural language; Hidden Markov model; Natural language processing; Word (group theory); Fuzzy logic; Linguistics","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":[0.0001105443,0.00006104098,0.0001321882,0.00006936032,0.00003692963,0.00004541946,0.0002130709,0.00003272806,0.00004710408],"category_scores_gemma":[0.00001706409,0.0000534993,0.00001874855,0.00021803,0.00001343433,0.00008029389,0.00003028074,0.00003315729,0.0001012683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000089766,"about_ca_system_score_gemma":0.00001055547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003837736,"about_ca_topic_score_gemma":0.000004424703,"domain_scores_codex":[0.9993784,0.00001382556,0.0001760901,0.0001921568,0.0001420637,0.00009739342],"domain_scores_gemma":[0.9995599,0.0000450193,0.00004879584,0.0002318208,0.00004095303,0.00007355013],"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":[0.000006762809,0.000104793,0.0004203257,0.000003196566,0.00000341472,2.233612e-7,0.0003941073,0.000001568765,0.05605626,0.06972511,0.004236354,0.8690479],"study_design_scores_gemma":[0.0007283206,0.0003051525,0.3497434,0.00002567303,0.00001417376,0.000007434139,0.0007734685,0.03547882,0.5860381,0.01594511,0.01045105,0.0004892817],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1526945,0.00003947096,0.5853475,0.007562942,0.0001154972,0.0003129063,0.000001288434,0.0002271752,0.2536987],"genre_scores_gemma":[0.8859287,0.000003900916,0.1131096,0.0007780115,0.00001270249,0.000004193277,8.531802e-7,0.00000163155,0.0001603736],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8685586,"threshold_uncertainty_score":0.2181638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06018352987154616,"score_gpt":0.3204660350669026,"score_spread":0.2602825051953565,"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."}}