{"id":"W2128604088","doi":"10.1109/tsa.2003.818031","title":"Incorporating the human hearing properties in the signal subspace approach for speech enhancement","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Speech and Audio Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":171,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Speech recognition; Speech enhancement; Computer science; Signal subspace; Noise (video); Spectrogram; Noise reduction; Residual; Colors of noise; Subspace topology; Filter (signal processing); Artificial intelligence; Algorithm; 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":["sts"],"consensus_categories":[],"category_scores_codex":[0.00126637,0.0002782925,0.0002364242,0.0001475058,0.001459964,0.0008763016,0.0005838064,0.00008160181,0.000004811769],"category_scores_gemma":[0.00001431458,0.0001699923,0.00007973565,0.0006894585,0.000150505,0.000706349,0.000005666936,0.0004567493,0.000003240756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006094757,"about_ca_system_score_gemma":0.0001602534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001816165,"about_ca_topic_score_gemma":0.00003265608,"domain_scores_codex":[0.9980316,0.0001366701,0.0003719706,0.0005565064,0.0003999976,0.000503276],"domain_scores_gemma":[0.9992371,0.0000924771,0.0001712705,0.0003330803,0.00009898572,0.00006706025],"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":[0.0000497525,0.0008618046,0.0002763733,0.0006223466,0.00004931337,0.00002191987,0.008717634,0.004270592,0.1882878,0.0006155778,0.00009974187,0.7961271],"study_design_scores_gemma":[0.0006763074,0.0001655638,0.00003615661,0.0002165071,0.00002214748,0.0001326748,0.001626281,0.01169885,0.9832575,0.001575719,0.0002471553,0.0003450922],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07527658,0.0005098885,0.9207963,0.0007757731,0.00008050226,0.0006221168,9.41648e-7,0.00006916092,0.001868776],"genre_scores_gemma":[0.8915676,0.00001389429,0.1073569,0.0005280014,0.00005483505,0.0001273876,6.187314e-7,0.00001863472,0.0003320435],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8162911,"threshold_uncertainty_score":0.99984,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04549423966659918,"score_gpt":0.264615521974624,"score_spread":0.2191212823080248,"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."}}