{"id":"W2096698602","doi":"10.1109/sipnn.1994.344815","title":"HMMs with mixtures of trend functions for automatic speech recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Speech recognition; TIMIT; Computer science; Set (abstract data type); Task (project management); State (computer science); Mixture model; Trajectory; Pattern recognition (psychology); SIGNAL (programming language); Artificial intelligence; Maximum likelihood; Mathematics; Algorithm; Statistics; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008821369,0.00008365118,0.0001231372,0.0001349577,0.00006589355,0.00004637209,0.0001651072,0.00003841039,0.001524037],"category_scores_gemma":[0.000043089,0.0000609624,0.00006585431,0.0002762523,0.00002790943,0.0002521295,0.00001437958,0.00003300465,0.0001297819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001031681,"about_ca_system_score_gemma":0.000007689056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008211487,"about_ca_topic_score_gemma":0.00004509803,"domain_scores_codex":[0.9993436,0.00002283843,0.0001665309,0.0001850096,0.0001491083,0.0001328995],"domain_scores_gemma":[0.9994023,0.0001827773,0.00006947169,0.0002154113,0.00008019969,0.00004979581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003125194,0.0001090677,0.00002786773,0.00001841009,0.00002275683,0.000001550419,0.00008444227,3.912927e-7,0.0004353327,0.0002166953,0.01181064,0.9872697],"study_design_scores_gemma":[0.003818175,0.00177969,0.002508242,0.0002787501,0.0001995644,0.0004288761,0.0005454175,0.4813228,0.4723249,0.01615739,0.01947098,0.001165277],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04839132,0.00007302885,0.8626481,0.001235864,0.0002733551,0.0004755887,0.00003659869,0.0005048127,0.08636134],"genre_scores_gemma":[0.1767701,0.00001165497,0.8159242,0.0003471019,0.00005635562,0.00008577057,0.00001326809,0.0000119147,0.006779688],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9861044,"threshold_uncertainty_score":0.9993887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04627982596179582,"score_gpt":0.2315993290325417,"score_spread":0.1853195030707459,"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."}}