{"id":"W1995668128","doi":"10.1109/mlsp.2007.4414294","title":"Single Channel Speech Separation using Minimum Mean Square Error Estimation of Sources' Log Spectra","year":2007,"lang":"en","type":"article","venue":"","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Minimum mean square error; Estimator; Mean squared error; Binary number; Gaussian; Mathematics; Algorithm; Mixture model; Statistics; Channel (broadcasting); Minimum-variance unbiased estimator; Computer science; Physics; 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":[0.0009265112,0.0001564163,0.0001885481,0.0003241678,0.00009390792,0.0001095576,0.0003947574,0.0001003644,0.00002468153],"category_scores_gemma":[0.00004121277,0.0001551035,0.00007400267,0.0005867705,0.00004962143,0.0007798835,0.00009026091,0.0001078649,0.00001760572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000884156,"about_ca_system_score_gemma":0.00005861334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009604172,"about_ca_topic_score_gemma":0.0001804133,"domain_scores_codex":[0.9984736,0.00006543531,0.0004706962,0.0003260757,0.00040331,0.0002608278],"domain_scores_gemma":[0.9989646,0.00008140053,0.0002629024,0.0004421992,0.0001734206,0.00007544486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001469837,0.002081617,0.0009343277,0.0002951879,0.0001180308,0.00006323792,0.05502224,0.07691541,0.530485,0.1746154,0.002474609,0.1568479],"study_design_scores_gemma":[0.0001387708,0.0001226664,0.0002292103,0.00002103223,0.000005461449,0.00002085282,0.0002035811,0.4139879,0.580843,0.004203388,0.00007369545,0.000150453],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2996625,0.00001512171,0.6961838,0.00016351,0.000086752,0.0002002666,7.55407e-7,0.0003092068,0.003378141],"genre_scores_gemma":[0.6899673,6.11686e-7,0.3096651,0.0001525745,0.00004006649,0.000001529631,0.000005541292,0.000009247239,0.0001580489],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3903048,"threshold_uncertainty_score":0.6324939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04563776900113702,"score_gpt":0.3238050090230323,"score_spread":0.2781672400218952,"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."}}