{"id":"W1976677479","doi":"10.1007/s10772-015-9276-6","title":"Feature selection for robust automatic speech recognition: a temporal offset approach","year":2015,"lang":"en","type":"article","venue":"International Journal of Speech Technology","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Speech recognition; Offset (computer science); Pattern recognition (psychology); Mel-frequency cepstrum; Feature selection; Artificial intelligence; Noise (video); Selection (genetic algorithm); Feature (linguistics); Feature extraction","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":[0.0008538262,0.0001850346,0.0003185566,0.00124632,0.00006445705,0.0001784077,0.001433479,0.0003029805,0.00003902267],"category_scores_gemma":[0.0007487368,0.0001653172,0.0001845884,0.0006621903,0.00007793523,0.0007403006,0.0001313994,0.0004193358,0.00005174612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002686353,"about_ca_system_score_gemma":0.0002831256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000767473,"about_ca_topic_score_gemma":0.00001098947,"domain_scores_codex":[0.9982233,0.00005618457,0.0004954202,0.0002819191,0.0006975232,0.0002456539],"domain_scores_gemma":[0.9966002,0.00009577879,0.0006075789,0.0002016444,0.002363004,0.0001317896],"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":[0.0000563809,0.0001914351,0.0006021734,0.000009706159,0.0001732096,0.00008819615,0.0000622904,0.00001268216,0.0003790312,0.001292437,0.02712698,0.9700055],"study_design_scores_gemma":[0.009997305,0.002418492,0.0004220284,0.0004949339,0.000184668,0.07194811,0.001798494,0.3562468,0.1450534,0.2188795,0.1911398,0.001416543],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05682033,0.0002124956,0.8928671,0.04373778,0.002916737,0.0004592279,0.00003179001,0.0004922154,0.002462263],"genre_scores_gemma":[0.04264664,0.00002109129,0.9559304,0.0003404811,0.0006254974,0.0000250758,0.00002006951,0.00001773979,0.0003729925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9685889,"threshold_uncertainty_score":0.674144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05480987488323085,"score_gpt":0.2838900785927865,"score_spread":0.2290802037095557,"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."}}