{"id":"W2148812765","doi":"10.1006/csla.1999.0136","title":"A path-stack algorithm for optimizing dynamic regimes in a statistical hidden dynamic model of speech","year":2000,"lang":"en","type":"article","venue":"Computer Speech & Language","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hidden Markov model; Utterance; Speech recognition; Stack (abstract data type); Path (computing); Phone; Reduction (mathematics); Set (abstract data type); Segmentation; Algorithm; Artificial intelligence; Pattern recognition (psychology)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004008134,0.0003127949,0.0005353741,0.0003033039,0.00006809785,0.0001490929,0.001022673,0.0001475407,0.0002603159],"category_scores_gemma":[0.0000288365,0.0003103375,0.0001756154,0.0004009352,0.00007899398,0.0003557634,0.000189064,0.0002206545,0.00006613815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001281104,"about_ca_system_score_gemma":0.0001113227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005844087,"about_ca_topic_score_gemma":0.00004827825,"domain_scores_codex":[0.9976202,0.0001072574,0.000587945,0.0007225515,0.0003909087,0.0005710861],"domain_scores_gemma":[0.9986186,0.000246937,0.000132993,0.000748742,0.00009648323,0.0001562676],"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":[0.00001578083,0.000137913,0.000005122647,0.00004656119,0.00002441828,0.0002284297,0.001116256,0.0003163192,0.0002722192,0.0004558542,0.0003122853,0.9970688],"study_design_scores_gemma":[0.0009268452,0.0001214357,0.0001176632,0.0001010242,0.00001477328,0.0001063903,0.00008634266,0.9948061,0.0008417174,0.002416707,0.0001032073,0.0003577757],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03637788,0.0001778248,0.9610587,0.0002470179,0.0001864838,0.0005122906,0.0001217097,0.0002007526,0.001117384],"genre_scores_gemma":[0.02450428,0.00004897817,0.9737893,0.0002568028,0.00005947689,0.00003949968,0.00005134418,0.00003708016,0.00121323],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9967111,"threshold_uncertainty_score":0.9999349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01325843623408658,"score_gpt":0.2679317228246664,"score_spread":0.2546732865905798,"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."}}