{"id":"W1930794383","doi":"10.1109/icassp.1987.1169578","title":"Integration of acoustic information in a large vocabulary word recognizer","year":2005,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Codebook; Computer science; Vector quantization; Speech recognition; Hidden Markov model; Vocabulary; Word (group theory); Linde–Buzo–Gray algorithm; Feature vector; Artificial intelligence; Learning vector quantization; Pattern recognition (psychology); Gaussian; Feature (linguistics); Curse of dimensionality; Set (abstract data type); Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001089122,0.0006624521,0.001162856,0.0005524826,0.0002746882,0.0006723832,0.001045282,0.0005837081,0.002701243],"category_scores_gemma":[0.004076225,0.0005554609,0.00041734,0.0004671519,0.0003949563,0.001917489,0.0008452592,0.0009451714,0.001923548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000303165,"about_ca_system_score_gemma":0.0005431238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002401924,"about_ca_topic_score_gemma":0.004572838,"domain_scores_codex":[0.9988883,0.0002057654,0.00009329263,0.0002245026,0.0005173683,0.00007082448],"domain_scores_gemma":[0.9984373,0.0007619757,0.00007159448,0.0002303353,0.0004450193,0.00005371381],"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":[0.0004506926,0.000241787,0.0008697462,0.0001245215,0.00007457774,0.00009650294,0.0001380856,0.02696967,0.1842183,0.002414438,0.001238232,0.7831634],"study_design_scores_gemma":[0.0001105595,0.001058818,0.00326137,0.0000374671,0.0001981174,0.0003827695,0.00008131243,0.7733358,0.2070167,0.004954124,0.009446514,0.0001165671],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02964485,0.000632732,0.9651294,0.000131968,0.0001387918,0.00006931737,0.0000407448,0.002990495,0.001221789],"genre_scores_gemma":[0.3427267,0.0004342675,0.6514122,0.0002177294,0.0001555577,0.0001297223,0.0003308778,0.000320846,0.004272181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002701243,"threshold_uncertainty_score":0.009036601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0160041604558046,"score_gpt":0.2416522779450447,"score_spread":0.2256481174892401,"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."}}