{"id":"W2121561087","doi":"10.1109/icassp.2000.862113","title":"An adaptive subspace approach for speech enhancement","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Speech enhancement; Subspace topology; Speech recognition; White noise; Noise (video); Computer science; Colors of noise; Gaussian noise; Energy (signal processing); Component (thermodynamics); Silence; Additive white Gaussian noise; Detector; Interference (communication); Eigenvalues and eigenvectors; Background noise; Gaussian; Speech processing; Noise measurement; Mathematics; Acoustics; Noise reduction; Artificial intelligence; Telecommunications; Statistics; Physics","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":[0.0001311355,0.00009650813,0.00009393436,0.00004198169,0.0001149837,0.0001561857,0.0005207401,0.00003206176,0.00006494593],"category_scores_gemma":[0.000007445299,0.00008029196,0.00003541027,0.0001889017,0.00002130986,0.0007181737,0.00004644074,0.00004587529,0.00003807996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002448244,"about_ca_system_score_gemma":0.00001178681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005298245,"about_ca_topic_score_gemma":0.000002886027,"domain_scores_codex":[0.9991025,0.00001197655,0.0000992886,0.0003552677,0.0001631547,0.0002677556],"domain_scores_gemma":[0.9994621,0.00001492878,0.00004041325,0.0003285916,0.00006435157,0.0000895611],"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":[0.00001457279,0.0006817915,0.00009633694,0.00003123467,0.00002593575,0.000006189502,0.001328786,0.0001443939,0.02938579,0.02304611,0.01372387,0.931515],"study_design_scores_gemma":[0.000332323,0.0003768197,0.00002212847,0.000005107041,0.000003291204,0.00000923718,0.0001153528,0.4233823,0.5709761,0.002252235,0.002306577,0.0002184265],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002326776,0.000110411,0.9661646,0.0004386388,0.00008245531,0.0001813345,3.730075e-7,0.0001456316,0.03054971],"genre_scores_gemma":[0.3065381,0.000003738429,0.6897404,0.0003605277,0.00006405194,0.00002422627,0.000001173007,0.000004603559,0.003263108],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9312966,"threshold_uncertainty_score":0.3274211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04340743612443945,"score_gpt":0.2596904436964959,"score_spread":0.2162830075720565,"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."}}