{"id":"W2105626703","doi":"10.1142/s0218001410008329","title":"PHONETIC SEGMENTATION OF EMOTIONAL SPEECH WITH HMM-BASED METHODS","year":2010,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"European Commission; McMaster University","keywords":"Segmentation; Computer science; Hidden Markov model; Speech segmentation; Speech recognition; Artificial intelligence; Process (computing); Pattern recognition (psychology)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068113,0.000123157,0.0001754813,0.0003837213,0.0000453371,0.0001466661,0.0004326194,0.00006138578,0.0006939138],"category_scores_gemma":[0.0001771255,0.0001025162,0.00009328687,0.0001752221,0.000123406,0.000415448,0.00003733561,0.000240111,0.00003346959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001868497,"about_ca_system_score_gemma":0.0000903596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001968634,"about_ca_topic_score_gemma":0.00003889985,"domain_scores_codex":[0.9984159,0.0001215418,0.0006245688,0.0001827534,0.0005409081,0.0001143648],"domain_scores_gemma":[0.9977673,0.0003410479,0.0005445834,0.0001082272,0.001138485,0.0001003855],"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":[0.00005139419,0.000165298,0.0003847508,0.000007516858,0.00004563217,0.00003230522,0.0001918128,0.00001345125,0.04228916,0.000353799,0.00000967123,0.9564552],"study_design_scores_gemma":[0.0002099966,0.000264121,0.001683734,0.0001738762,0.00002476309,0.0005648436,0.0002789975,0.02067946,0.9535561,0.02228795,0.00009021414,0.0001859684],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2672021,0.000008505041,0.7307821,0.0009076898,0.0008570915,0.00006194528,0.00001455255,0.00001222742,0.0001537416],"genre_scores_gemma":[0.6792536,0.00002146737,0.3202134,0.000327947,0.0001605365,0.000002929923,0.000007942184,0.00000623748,0.000005910646],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9562693,"threshold_uncertainty_score":0.7597869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07410581644215461,"score_gpt":0.3492316905540887,"score_spread":0.2751258741119341,"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."}}