{"id":"W2167894290","doi":"","title":"Subspace-based speech enhancement by updating noise characteristics in the presence of speech","year":2008,"lang":"en","type":"article","venue":"European Signal Processing Conference","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton; Institut National de la Recherche Scientifique","funders":"","keywords":"Subspace topology; Signal subspace; Speech enhancement; Speech recognition; Computer science; Noise (video); Principal component analysis; Distortion (music); Variance (accounting); Pattern recognition (psychology); Noise reduction; Noise measurement; SIGNAL (programming language); Selection (genetic algorithm); Signal-to-noise ratio (imaging); Artificial intelligence; Algorithm; Telecommunications","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":[0.00125456,0.0002806019,0.0003080317,0.0001248042,0.000313137,0.000342095,0.002000352,0.00004149498,0.00004549241],"category_scores_gemma":[0.000153076,0.0002223777,0.00005378553,0.0007683424,0.0002520261,0.0006339429,0.0002049007,0.0003877725,0.00004172556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003342576,"about_ca_system_score_gemma":0.0004367094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001811959,"about_ca_topic_score_gemma":0.000003169746,"domain_scores_codex":[0.997127,0.000383948,0.000634292,0.0005900412,0.00076911,0.0004956122],"domain_scores_gemma":[0.9983941,0.0001601156,0.0005326994,0.0005022833,0.0003174411,0.00009338028],"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":[0.00004986767,0.0004223232,0.007752987,0.0003407096,0.00001018636,0.0006198949,0.0059603,0.00004318227,0.2767316,0.0001863775,0.001299315,0.7065832],"study_design_scores_gemma":[0.001167657,0.0003469761,0.009258183,0.001429211,0.00001653378,0.0001737575,0.0003503305,0.04916725,0.9341198,0.0002935398,0.002783417,0.0008933342],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4257541,0.0003237477,0.560376,0.0009154858,0.00008053971,0.0002686092,0.00000607479,0.0001182891,0.0121571],"genre_scores_gemma":[0.9644376,0.00002653074,0.03469006,0.0005477562,0.00008631514,0.000006670949,0.00001101542,0.00002060849,0.0001734173],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7056898,"threshold_uncertainty_score":0.90683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03058665329831157,"score_gpt":0.2454176022873812,"score_spread":0.2148309489890696,"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."}}