{"id":"W2157458051","doi":"10.1109/icassp.1988.196631","title":"Modeling acoustic-phonetic detail in an HMM-based large vocabulary speech recognizer","year":2003,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Hidden Markov model; Computer science; Speech recognition; Word (group theory); Vocabulary; Context (archaeology); Vowel; Set (abstract data type); Artificial intelligence; Duration (music); Natural language processing; Acoustics; Linguistics","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":[0.0008083299,0.0001924069,0.0002194188,0.0002803964,0.00009391868,0.000171756,0.0004895166,0.0001218737,0.0009699531],"category_scores_gemma":[0.0001989391,0.0001808025,0.00007745373,0.0005604493,0.0000165402,0.0004556596,0.00004541649,0.0001832435,0.0004350909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005013715,"about_ca_system_score_gemma":0.0001385391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003936131,"about_ca_topic_score_gemma":0.0005889198,"domain_scores_codex":[0.9980597,0.0002347898,0.0003470202,0.0005458502,0.0003181581,0.000494447],"domain_scores_gemma":[0.9989672,0.0001115772,0.00003664811,0.0005808268,0.0001185293,0.0001852596],"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":[0.0001172924,0.005209363,0.01547781,0.0001618308,0.00008858526,0.001646621,0.001675903,0.04920712,0.02888176,0.01295192,0.001713366,0.8828684],"study_design_scores_gemma":[0.0007335047,0.0000472146,0.0001805104,0.00002352635,0.000006713301,0.00002311517,0.0001009784,0.9799303,0.01648965,0.001933671,0.0002338999,0.0002969478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2122192,0.00004322964,0.7793927,0.0001640071,0.0002047445,0.0001579457,0.000001792982,0.000205773,0.007610585],"genre_scores_gemma":[0.7235612,0.000007120315,0.2746884,0.001450349,0.00001779489,0.00001643797,0.00000327312,0.00001508013,0.0002403555],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9307231,"threshold_uncertainty_score":0.9999433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03335114007634879,"score_gpt":0.2593127218804179,"score_spread":0.2259615818040691,"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."}}