{"id":"W2080551551","doi":"10.1186/s13636-014-0042-5","title":"Homogenous ensemble phonotactic language recognition based on SVM supervector reconstruction","year":2014,"lang":"en","type":"article","venue":"EURASIP Journal on Audio Speech and Music Processing","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"GLS Industries (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Phonotactics; Support vector machine; Word error rate; NIST; Speech recognition; Language model; Artificial intelligence; Pattern recognition (psychology); Feature vector","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":[0.0008150538,0.0002491956,0.000272383,0.0004042423,0.0005816699,0.0007111728,0.000265458,0.0001028381,0.000182492],"category_scores_gemma":[0.000443651,0.0002130284,0.0001106626,0.0003716298,0.00004899854,0.000680253,0.00002640722,0.000468156,0.0001536805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009858148,"about_ca_system_score_gemma":0.0001285218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000575724,"about_ca_topic_score_gemma":0.00001055236,"domain_scores_codex":[0.9981694,0.0002368453,0.0003558176,0.0004310253,0.0004229861,0.0003839509],"domain_scores_gemma":[0.998785,0.0002300791,0.0002915933,0.0002476055,0.0001756202,0.0002701086],"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":[0.00004844601,0.00008924657,0.00006836885,0.00003123534,0.000009283609,0.00008096567,0.0002851917,0.00000428523,0.008844721,0.00001799227,0.000212127,0.9903082],"study_design_scores_gemma":[0.009561072,0.004548177,0.01198465,0.004982944,0.000240942,0.02531289,0.001371174,0.1587029,0.7566338,0.01355819,0.009733079,0.003370238],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8442683,0.0001990745,0.137811,0.001739783,0.001177362,0.0001904874,0.000004069517,0.0002672889,0.01434267],"genre_scores_gemma":[0.9386086,0.00004607918,0.05682711,0.003776899,0.000587592,0.000006907139,0.000003725879,0.00002733917,0.0001157536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9869379,"threshold_uncertainty_score":0.8687046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02324670592973778,"score_gpt":0.2328707149487062,"score_spread":0.2096240090189684,"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."}}