{"id":"W2010610249","doi":"10.1117/12.458389","title":"<title>Robust speech separation using visually constructed speech signals</title>","year":2002,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"SIGNAL (programming language); Speech recognition; Computer science; Envelope (radar); Basis (linear algebra); Separation (statistics); Artificial intelligence; Ideal (ethics); Speech processing; Mathematics; Machine learning","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":[0.0003074011,0.0002291858,0.0002621706,0.0001113204,0.00009136926,0.0002203492,0.0008643729,0.0001579786,0.0001780008],"category_scores_gemma":[0.0002144656,0.0002043721,0.0002834197,0.0004320536,0.0001329511,0.0005914962,0.0001511523,0.0002115341,0.00003868134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000118144,"about_ca_system_score_gemma":0.00003846057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001323424,"about_ca_topic_score_gemma":6.851526e-8,"domain_scores_codex":[0.9982918,2.763953e-8,0.0004356716,0.0003427251,0.0006087704,0.0003210127],"domain_scores_gemma":[0.9985456,0.00005743721,0.0002681049,0.00006653704,0.0009657178,0.00009664146],"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":[0.000009478621,0.00007608034,0.00005559898,0.0001916756,0.0001549427,5.912498e-7,0.00009674843,0.0001017613,0.7798728,0.1939013,0.01967794,0.005861037],"study_design_scores_gemma":[0.0008336655,0.0001922803,0.00009753354,0.0003903212,0.0001086932,0.0001370843,0.0001507491,0.4082251,0.5644415,0.003293527,0.02148163,0.0006478851],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.962805,0.0002244638,0.001808951,0.0007461314,0.0004188835,0.000256902,0.00001261607,0.000159556,0.03356748],"genre_scores_gemma":[0.1905938,0.0001354611,0.8064206,0.0002200681,0.0008544946,0.00002676183,0.000006292876,0.00007030725,0.001672187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8046117,"threshold_uncertainty_score":0.8334051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02047577790109141,"score_gpt":0.248604112670916,"score_spread":0.2281283347698246,"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."}}