{"id":"W1998948935","doi":"10.1109/iciet.2007.4381302","title":"Speaker Accent Classification System Using a Fuzzy Gaussian Classifier","year":2007,"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":"Mixture model; Stress (linguistics); Hidden Markov model; Computer science; Pattern recognition (psychology); Artificial intelligence; Speech recognition; Vector quantization; Fuzzy logic; Gaussian; Classifier (UML); Cluster analysis; Phonetic transcription; Speaker recognition; Fuzzy clustering; Feature vector; Speaker diarisation","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":[0.00147236,0.0005239829,0.001025137,0.0009205702,0.0007908315,0.000772568,0.0009601201,0.00095097,0.00226344],"category_scores_gemma":[0.001534713,0.0003052476,0.0006185619,0.0004673616,0.0002944485,0.0008094504,0.0005636662,0.0007795852,0.001847866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007644595,"about_ca_system_score_gemma":0.0007443917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008518267,"about_ca_topic_score_gemma":0.006210938,"domain_scores_codex":[0.9992691,0.00008746955,0.00004491969,0.0002234374,0.000288901,0.00008624733],"domain_scores_gemma":[0.9992226,0.0001117319,0.00004046791,0.00005554461,0.0005202559,0.00004929834],"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":[0.0009340814,0.0003199929,0.004274306,0.0001004416,0.0001739746,0.0001762693,0.0002797356,0.02765985,0.08137091,0.002652671,0.006171408,0.8758864],"study_design_scores_gemma":[0.00004947833,0.0001441247,0.004001949,0.00001271985,0.00008644172,0.0002340596,0.00006132127,0.9612808,0.02928541,0.001184139,0.003594257,0.00006530585],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05134907,0.0003687641,0.9393408,0.0001666229,0.0002388042,0.0001271347,0.0001462067,0.005490122,0.0027725],"genre_scores_gemma":[0.598954,0.0002893167,0.3911418,0.0001962507,0.000117024,0.0001516153,0.0003519257,0.0001024778,0.008695649],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008518267,"threshold_uncertainty_score":0.01693738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08100266918697686,"score_gpt":0.2962460351512798,"score_spread":0.215243365964303,"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."}}