{"id":"W2883127466","doi":"10.1109/icassp.2018.8461788","title":"Multi-Scenario Deep Learning for Multi-Speaker Source Separation","year":2018,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministère de la Santé et des Services sociaux","keywords":"Computer science; Source separation; Matching (statistics); Separation (statistics); Artificial intelligence; Deep learning; Data modeling; Machine learning; Database","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002233347,0.0001133985,0.0001024341,0.00005970735,0.0003862984,0.0002808835,0.0003533822,0.00005977328,0.00003256743],"category_scores_gemma":[0.0001066081,0.00009743882,0.00005200856,0.000185294,0.0000423711,0.0005430466,0.000104019,0.00009153078,0.0002422479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002720789,"about_ca_system_score_gemma":0.00003553573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001563413,"about_ca_topic_score_gemma":0.0001540193,"domain_scores_codex":[0.999034,0.0000239475,0.0001584799,0.0003515931,0.000127409,0.0003045176],"domain_scores_gemma":[0.9994192,0.00004006793,0.00007809322,0.000207682,0.000177345,0.00007767102],"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":[0.0000246846,0.000197266,0.00638801,0.00003669498,0.00003172805,0.000003191829,0.007388278,0.001332592,0.08333112,0.0004725543,0.001593712,0.8992001],"study_design_scores_gemma":[0.0006330349,0.00009276198,0.00147391,0.00001066436,0.000003160998,0.000006314689,0.00006519744,0.8487625,0.1153817,0.00004057751,0.03336613,0.0001640772],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009894563,0.00006601739,0.9883071,0.00024006,0.0002115896,0.0001469775,8.524641e-8,0.0003354889,0.0007980961],"genre_scores_gemma":[0.2539807,0.000001600365,0.7367823,0.0005000149,0.000174891,0.00001167336,0.000001956071,0.000009955544,0.008536923],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8990361,"threshold_uncertainty_score":0.397344,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04451585460580375,"score_gpt":0.3239678072055122,"score_spread":0.2794519525997085,"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."}}