{"id":"W2104046483","doi":"10.1109/isspa.2001.950249","title":"Hybrid architectures for complex phonetic features classification: a unified approach","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Computer science; Hidden Markov model; Speech recognition; Artificial intelligence; Artificial neural network; Classifier (UML); Pattern recognition (psychology); Boosting (machine learning); Backpropagation; Learning vector quantization; Vector quantization; Time delay neural network; Machine learning","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":[0.0001052737,0.0001236293,0.0001374124,0.0001136773,0.0001449167,0.0001585009,0.0005721289,0.00003494227,0.0004032548],"category_scores_gemma":[0.00005285786,0.00009906266,0.00009653104,0.0001654626,0.00004829213,0.00004053092,0.00004547101,0.00007334701,0.0001032101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001456411,"about_ca_system_score_gemma":0.000008826879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005342232,"about_ca_topic_score_gemma":0.000002467667,"domain_scores_codex":[0.9990329,0.00004922849,0.0001566385,0.000356966,0.0001828287,0.0002214798],"domain_scores_gemma":[0.9991937,0.0001789874,0.0000489257,0.00042463,0.00006391437,0.00008979875],"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":[0.00001120074,0.0002949315,0.00002113501,0.00003446014,0.0000380209,0.000003565306,0.0004265924,0.00003251613,0.002560024,0.05456191,0.1219359,0.8200798],"study_design_scores_gemma":[0.0007510034,0.00008424558,0.008894391,0.000007620253,0.00001320796,0.0001883766,0.00008535333,0.931653,0.01024015,0.01312717,0.0345431,0.0004123354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002672145,0.00007693093,0.8556696,0.003313686,0.0001076026,0.0003804289,0.000007590899,0.0003540386,0.1374179],"genre_scores_gemma":[0.5778649,0.000004254926,0.417321,0.00115094,0.00006517618,0.00007799664,0.000007107004,0.000007459361,0.003501165],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9316205,"threshold_uncertainty_score":0.4415357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0997431855592085,"score_gpt":0.2613932056576351,"score_spread":0.1616500200984266,"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."}}