{"id":"W2544551282","doi":"10.1109/icscs.2009.5412292","title":"Combined speech decoders output for phoneme recognition enhancement","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Speech recognition; Mel-frequency cepstrum; Robustness (evolution); Feature extraction; Pattern recognition (psychology); Normalization (sociology); Cepstrum; Artificial intelligence; Naive Bayes classifier; Classifier (UML); Support vector machine; Speaker recognition; Speech enhancement; Noise reduction","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":[0.0002644852,0.0001280672,0.0001483548,0.0001147375,0.0001107721,0.0001318755,0.000341157,0.00005608999,0.0004015926],"category_scores_gemma":[0.0000741828,0.000117547,0.0001062321,0.0001862037,0.00001280409,0.0003065477,0.00002539083,0.00004704486,0.0005455394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000403292,"about_ca_system_score_gemma":0.00003166587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000060841,"about_ca_topic_score_gemma":0.000006795377,"domain_scores_codex":[0.9989187,0.0000269448,0.0002380286,0.0003388179,0.000203997,0.0002734727],"domain_scores_gemma":[0.9993047,0.0001084955,0.00006535499,0.0002803774,0.0001425196,0.00009852953],"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":[0.00001849087,0.0001478957,0.000004004889,0.000003512862,0.000009679002,0.000002511078,0.00005929684,1.907717e-7,0.001893411,0.001740202,0.01222204,0.9838988],"study_design_scores_gemma":[0.002717124,0.001078324,0.000770198,0.00004954807,0.0000253036,0.00001968919,0.000115563,0.03842827,0.8195334,0.1153146,0.02122123,0.0007267296],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01212222,0.00001100879,0.9436637,0.004585039,0.0003732602,0.0004391263,0.000003560365,0.0002856807,0.03851644],"genre_scores_gemma":[0.1955065,0.00003363152,0.7924504,0.007210943,0.00008287327,0.00006566248,0.00002728366,0.000008742586,0.004613867],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9831721,"threshold_uncertainty_score":0.7011987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04394314540733342,"score_gpt":0.2670386047160946,"score_spread":0.2230954593087612,"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."}}