{"id":"W1829432249","doi":"10.1109/icassp.1994.389344","title":"Application of vector quantized hidden Markov modeling to telephone network based connected digit recognition","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Codebook; Hidden Markov model; Speech recognition; Telephone network; Computer science; Telephony; Pattern recognition (psychology); Artificial intelligence; Markov model; Markov chain; Machine learning; Telecommunications","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":[],"consensus_categories":[],"category_scores_codex":[0.0002014338,0.0001294259,0.0002156555,0.0001421691,0.00007223568,0.00007498595,0.0003508548,0.000071881,0.0007341017],"category_scores_gemma":[0.0001386007,0.000124439,0.00008155693,0.0007903579,0.00001260435,0.0002209282,0.0000503011,0.00006115554,0.0005785671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002921512,"about_ca_system_score_gemma":0.00001508014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005500486,"about_ca_topic_score_gemma":0.00002226867,"domain_scores_codex":[0.9987084,0.00007529047,0.0003572887,0.0003630482,0.0002564402,0.0002395887],"domain_scores_gemma":[0.9989098,0.000239903,0.00009698101,0.00040138,0.0002302952,0.0001216208],"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":[0.00002888465,0.0001278527,0.00007468167,0.00001398447,0.00001704782,0.000001541241,0.00005861219,0.0005165989,0.005510531,0.0003686683,0.001777627,0.991504],"study_design_scores_gemma":[0.0004153704,0.00004705092,0.0001287238,0.00003444785,0.000008288413,0.000002783631,0.00001121302,0.9794082,0.01861858,0.0007305909,0.0004064554,0.0001882913],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04160754,0.0000163702,0.9499053,0.0009513518,0.0001280038,0.0002725955,0.000006043428,0.000310779,0.00680206],"genre_scores_gemma":[0.6829075,0.000007055953,0.3161458,0.0006522175,0.00006200444,0.00006048995,0.00001261403,0.00001021136,0.0001422049],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9913157,"threshold_uncertainty_score":0.8037899,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04209136715797211,"score_gpt":0.2318102425224035,"score_spread":0.1897188753644314,"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."}}