{"id":"W1966053902","doi":"10.1109/mlsp.2009.5306201","title":"Gain estimation in model-based single channel speech separation","year":2009,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University; Carleton University; University of Toronto","funders":"","keywords":"Computer science; Channel (broadcasting); Source separation; Maximum likelihood; SIGNAL (programming language); Speech recognition; Energy (signal processing); Separation (statistics); Algorithm; Mathematics; Statistics; Machine learning; Telecommunications","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":[0.0001615904,0.00007313654,0.00007209257,0.0001212748,0.00004570246,0.0001404646,0.0002021147,0.00003855388,0.000003513535],"category_scores_gemma":[0.00002429897,0.0000691453,0.00001826747,0.0003458723,0.000006397285,0.0006323754,0.00001265981,0.00005091216,0.00002454234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005081162,"about_ca_system_score_gemma":0.00005992907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000440785,"about_ca_topic_score_gemma":0.00001604834,"domain_scores_codex":[0.9993344,0.0000145421,0.0001364019,0.0002010131,0.000148572,0.0001650964],"domain_scores_gemma":[0.9997084,0.00001319441,0.00004020599,0.0001677615,0.00003383635,0.0000366297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000439098,0.0001304218,0.000021097,0.000005689092,5.181178e-7,0.000006674404,0.0001835711,0.6555699,0.02301427,0.001073669,0.000328972,0.3196609],"study_design_scores_gemma":[0.0001406031,0.00003690412,0.0000833794,0.00001166873,3.818381e-7,0.000001492227,0.000002673107,0.6916377,0.2909925,0.01702446,0.000004127003,0.00006408617],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02982356,0.00002013202,0.9626224,0.001948456,0.00003588258,0.00007042579,1.056617e-7,0.0001477477,0.005331262],"genre_scores_gemma":[0.6656474,3.144772e-7,0.3332427,0.0009760267,0.000009754683,0.000001583297,0.000002098188,0.000001641663,0.0001184668],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6358239,"threshold_uncertainty_score":0.2819663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02479060202509689,"score_gpt":0.2863974212305902,"score_spread":0.2616068192054933,"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."}}