{"id":"W2119901478","doi":"10.1109/tasl.2007.901310","title":"Soft Mask Methods for Single-Channel Speaker Separation","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Audio Speech and Language Processing","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Spectrogram; Computer science; SIGNAL (programming language); Speech recognition; Binary number; Channel (broadcasting); Masking (illustration); Source separation; Speech enhancement; Speech processing; Algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Telecommunications; Noise reduction","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007229979,0.000897027,0.0006524281,0.000851231,0.0004402519,0.0008144411,0.0009989167,0.0008766694,0.00507943],"category_scores_gemma":[0.00270405,0.0003718921,0.0005898434,0.0006873528,0.0006325301,0.001198721,0.001117859,0.001160739,0.00253094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003978041,"about_ca_system_score_gemma":0.0006748012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001546393,"about_ca_topic_score_gemma":0.001700083,"domain_scores_codex":[0.9994276,0.0001186563,0.00002197757,0.0000835338,0.000313364,0.00003484233],"domain_scores_gemma":[0.999172,0.0004902885,0.00006013064,0.0001073896,0.0001423763,0.00002789372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004964418,0.00006241463,0.0002963208,0.0003425784,0.00008628125,0.0001171932,0.0001748823,0.1208082,0.04698643,0.03722503,0.004382018,0.7890222],"study_design_scores_gemma":[0.0000352302,0.00007442693,0.000389332,0.00003134918,0.00002703554,0.00020789,0.00003592996,0.9311491,0.02240516,0.036592,0.009017881,0.00003467564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002151676,0.0005195223,0.9960068,0.00005171192,0.00003959083,0.00002283018,0.00003889787,0.000342641,0.0008263239],"genre_scores_gemma":[0.07865454,0.001264867,0.9144138,0.00009767563,0.000161156,0.0001444131,0.0002210488,0.0001762627,0.004866268],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00507943,"threshold_uncertainty_score":0.01699233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0249877122083876,"score_gpt":0.338796042543846,"score_spread":0.3138083303354585,"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."}}