{"id":"W2146471910","doi":"10.1109/icassp.2005.1415066","title":"Non-Intrusive GMM-Based Speech Quality Measurement","year":2006,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Consistency (knowledge bases); Speech recognition; Quality (philosophy); Mixture model; Multivariate statistics; Gaussian; Artificial intelligence; Linear predictive coding; Regression analysis; Regression; Speech processing; Pattern recognition (psychology); Machine learning; Statistics; Mathematics","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":[0.0006390531,0.0001239455,0.0001382263,0.00006278393,0.000123767,0.0002142103,0.0005424991,0.00004126307,0.00007159023],"category_scores_gemma":[0.00003456325,0.0001029229,0.00006444253,0.0003049645,0.00002709914,0.0002622887,0.00007975876,0.00007792597,0.0001609877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009535924,"about_ca_system_score_gemma":0.0001859252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004505076,"about_ca_topic_score_gemma":0.0002496036,"domain_scores_codex":[0.9984242,0.00002919729,0.0002414676,0.000345555,0.0006629513,0.0002966256],"domain_scores_gemma":[0.9991496,0.00002504632,0.00008723697,0.0004314279,0.0002389431,0.00006775762],"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":[0.00004808083,0.001169053,0.02902287,0.0002256928,0.0000565878,0.0001822648,0.0002805107,0.001207881,0.3130691,0.02682931,0.08460032,0.5433083],"study_design_scores_gemma":[0.0004631179,0.00003038261,0.01290603,0.00002041699,0.00000273012,0.000003376892,0.000009864987,0.003199465,0.9745588,0.00553106,0.003052403,0.0002223788],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02649175,0.00005506481,0.9188258,0.002664486,0.0002062279,0.0001138464,4.805235e-7,0.0002563879,0.05138594],"genre_scores_gemma":[0.8017835,3.630255e-7,0.1964292,0.00124474,0.0001145573,0.000005960646,0.000001256345,0.000005374522,0.00041507],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7752917,"threshold_uncertainty_score":0.4197074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02783214041702075,"score_gpt":0.2656081218745382,"score_spread":0.2377759814575174,"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."}}