{"id":"W2136652457","doi":"10.1109/icassp.2004.1326116","title":"A Viterbi algorithm for a trajectory model derived from HMM with explicit relationship between static and dynamic features","year":2004,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Pratt and Whitney Canada","keywords":"Viterbi algorithm; Hidden Markov model; Soft output Viterbi algorithm; Forward algorithm; Computer science; Iterative Viterbi decoding; Trajectory; Speech recognition; Sequence (biology); Algorithm; State (computer science); Pattern recognition (psychology); Artificial intelligence; Markov model; Machine learning; Markov chain; Decoding methods; Variable-order Markov model","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":[0.00008015899,0.000130622,0.0001591378,0.00009814195,0.0001225739,0.0001284277,0.0001884802,0.00006007502,0.000005780396],"category_scores_gemma":[0.00002778827,0.0001027871,0.00003912186,0.0001251321,0.00002787024,0.0003269309,0.0000291473,0.00008102698,0.000006276609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004360344,"about_ca_system_score_gemma":0.00006831669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007266386,"about_ca_topic_score_gemma":0.0001339552,"domain_scores_codex":[0.9991843,0.0000242345,0.0001382779,0.0003299428,0.0001474455,0.0001758101],"domain_scores_gemma":[0.9991375,0.0004587114,0.0000478831,0.000211909,0.00004437503,0.00009962997],"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":[0.00004782096,0.0002005766,0.0039282,0.00005257591,0.0002092784,0.00002224563,0.007278976,0.0008819221,0.002129868,0.01005317,0.0001789206,0.9750165],"study_design_scores_gemma":[0.002444379,0.0001933408,0.1049472,0.00008455104,0.00006537494,0.00001748306,0.000313761,0.7764768,0.004784265,0.1101812,0.00001301312,0.0004786255],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2160088,0.0000318538,0.7828764,0.0005400665,0.00001421259,0.0002239206,0.00003942261,0.0001205051,0.0001447916],"genre_scores_gemma":[0.4657724,0.000001855765,0.5338377,0.0002094432,0.000009403519,0.00004281231,0.00001221963,0.000007294418,0.0001069064],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9745378,"threshold_uncertainty_score":0.4191537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03367362737486818,"score_gpt":0.2606226382829699,"score_spread":0.2269490109081017,"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."}}