{"id":"W2030534537","doi":"10.1016/j.specom.2007.04.007","title":"Monaural speech segregation based on fusion of source-driven with model-driven techniques","year":2007,"lang":"en","type":"article","venue":"Speech Communication","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Codebook; Speech recognition; Monaural; Source separation; Spectral envelope; Estimator; A priori and a posteriori; Speech coding; Algorithm; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006937169,0.0001952095,0.0002089429,0.0003023658,0.0002359838,0.00008826025,0.001325166,0.000126822,0.000005242205],"category_scores_gemma":[0.00004565345,0.0001697504,0.00006239284,0.0006562066,0.0001087015,0.0005488519,0.000232969,0.0002890735,0.000009882424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001263952,"about_ca_system_score_gemma":0.000112013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006267484,"about_ca_topic_score_gemma":0.0001026333,"domain_scores_codex":[0.9983379,0.00009101233,0.0003752828,0.0003212569,0.0005956476,0.0002788603],"domain_scores_gemma":[0.997558,0.0001225889,0.0003765188,0.001504679,0.0003562568,0.00008194061],"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":[0.0001523502,0.0003190445,0.002789064,0.0000507492,0.00001482681,0.000006500023,0.0007954547,0.01918821,0.1079873,0.002033686,0.0002220322,0.8664408],"study_design_scores_gemma":[0.0002931983,0.0001750573,0.0006773836,0.00020955,0.000007414609,0.000009032946,0.00003640033,0.3665683,0.6301605,0.001427484,0.0002611946,0.0001745323],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1901927,0.00004372745,0.8006974,0.0009904177,0.00002017426,0.0003228243,0.000001767743,0.000359238,0.007371734],"genre_scores_gemma":[0.5395692,0.00001515369,0.4601377,0.0001631425,0.00001165241,0.000006514677,0.00001866801,0.00001229519,0.00006566752],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8662663,"threshold_uncertainty_score":0.6922221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01507833896096016,"score_gpt":0.2599297186008326,"score_spread":0.2448513796398724,"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."}}