{"id":"W2102232231","doi":"10.1109/scw.2002.1215761","title":"Preprocessing of noisy speech for voice coders","year":2003,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Speech recognition; Computer science; Preprocessor; Speech coding; Linear predictive coding; Voice activity detection; Speech enhancement; Speech processing; Harmonic Vector Excitation Coding; Coding (social sciences); Block (permutation group theory); PSQM; Noise reduction; Artificial intelligence; Mathematics; Statistics","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":[0.0002833513,0.00007760154,0.0001154169,0.00005177502,0.0000823606,0.00008430889,0.0003511532,0.00003477205,0.00001196718],"category_scores_gemma":[0.0001732807,0.00006699854,0.00004515683,0.0002694761,0.00002811612,0.0004121336,0.00003347132,0.00003832233,0.000009497565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001125085,"about_ca_system_score_gemma":0.0001157281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004079677,"about_ca_topic_score_gemma":0.000004277519,"domain_scores_codex":[0.9992099,0.00001258163,0.0001687276,0.0002583011,0.0001444488,0.0002060091],"domain_scores_gemma":[0.9993981,0.000076381,0.00008820793,0.0002560006,0.0001326772,0.00004862011],"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":[0.00002719224,0.0003446394,0.004998403,0.0008082101,0.00006246218,0.00001015943,0.002105045,0.0003357859,0.287212,0.04444451,0.006659461,0.6529921],"study_design_scores_gemma":[0.0002704531,0.00003341039,0.00004903887,0.00002571635,0.000003386629,0.0000125014,0.00005917674,0.00251712,0.9823782,0.009594925,0.00495174,0.0001043578],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01817036,0.0001622367,0.9520489,0.0002179887,0.0001170739,0.0001042588,4.332236e-7,0.00009186357,0.02908687],"genre_scores_gemma":[0.4008893,0.000001872484,0.5979245,0.000270896,0.00001453201,0.000005015523,2.612314e-7,0.000005072231,0.0008885668],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6951662,"threshold_uncertainty_score":0.2732121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02063687337524109,"score_gpt":0.2694632717330872,"score_spread":0.2488263983578461,"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."}}