{"id":"W168718579","doi":"10.1007/3-540-27489-8_7","title":"Signal Subspace Techniques for Speech Enhancement","year":2005,"lang":"en","type":"book-chapter","venue":"Signals and communication technology","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Speech enhancement; Speech recognition; Subspace topology; SIGNAL (programming language); Residual; Frequency domain; Distortion (music); Signal subspace; Noise (video); Perspective (graphical); Domain (mathematical analysis); Artificial intelligence; Algorithm; Noise reduction; Telecommunications; Mathematics; Computer vision","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003346048,0.0003012563,0.0003862927,0.000405523,0.000297622,0.0001328498,0.00171995,0.0005694363,0.00008945376],"category_scores_gemma":[0.00001579322,0.0003030394,0.00008389832,0.0001017965,0.0002420511,0.0001961973,0.000723699,0.0004357414,0.00002412308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000630356,"about_ca_system_score_gemma":0.00009467208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002144672,"about_ca_topic_score_gemma":0.00001519459,"domain_scores_codex":[0.9986537,0.00001601776,0.0003901412,0.0004863338,0.0001731947,0.0002805816],"domain_scores_gemma":[0.9979016,0.0001081366,0.0004053365,0.001283548,0.000246021,0.00005533542],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004072248,0.00001914236,0.000001699163,0.00002599276,0.00002667941,0.000001060103,0.00002899234,1.646742e-7,0.005498581,0.235904,0.00136594,0.7571236],"study_design_scores_gemma":[0.0001307185,0.0001642988,3.840191e-7,0.0002015348,0.00001672843,0.00002412056,0.000009967801,0.000119136,0.3341657,0.2682859,0.396587,0.0002945491],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006123318,0.03591669,0.7322868,0.02459591,0.00005761107,0.001220052,0.00001461831,0.001386361,0.2044608],"genre_scores_gemma":[0.01832614,0.01182775,0.8433787,0.001112879,0.0001243971,0.0003429821,0.00004531074,0.00006916308,0.1247727],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7568291,"threshold_uncertainty_score":0.9999422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01862485102146598,"score_gpt":0.2668659399757683,"score_spread":0.2482410889543023,"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."}}