{"id":"W4235027941","doi":"10.1109/icme.2003.1221723","title":"Robust variational speech separation using fewer microphones than speakers","year":2003,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Source separation; Speech recognition; Computer science; Microphone; Probabilistic logic; Microphone array; Noise (video); Separation (statistics); Speech processing; Inference; Speech enhancement; Multilateration; Background noise; Algorithm; Acoustics; Artificial intelligence; Machine learning; Telecommunications; Physics","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":[0.0002183739,0.0001069448,0.00008938797,0.00007903981,0.0001787326,0.0002878543,0.0002337363,0.00004726106,0.0001430911],"category_scores_gemma":[0.0000372858,0.00009634137,0.00003977255,0.0003894171,0.00001871605,0.0006682121,0.00003845531,0.00006485041,0.0001037375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005087969,"about_ca_system_score_gemma":0.0001583194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002962635,"about_ca_topic_score_gemma":0.00002090581,"domain_scores_codex":[0.9990633,0.00004057363,0.0001586611,0.0002871099,0.0002288541,0.0002214848],"domain_scores_gemma":[0.9995372,0.00002577308,0.00007007982,0.000208277,0.00009730711,0.00006132357],"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":[0.00001895147,0.0003619521,0.02082758,0.00005914183,0.0001012267,0.00009275368,0.001593146,0.03245168,0.8422568,0.06520199,0.007568163,0.02946655],"study_design_scores_gemma":[0.0004324939,0.00002621091,0.002565345,0.00001923376,0.000008127373,0.0001917815,0.00007449713,0.05520567,0.9314255,0.006029222,0.003653086,0.0003688506],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1218494,0.00005966495,0.8686862,0.0002328867,0.0004613522,0.00005939836,3.869204e-7,0.00009307523,0.008557589],"genre_scores_gemma":[0.2388884,0.00000274365,0.7596187,0.0003529017,0.00008313909,0.000001097674,0.000001762392,0.000006406997,0.001044785],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.117039,"threshold_uncertainty_score":0.3928687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0384348062454747,"score_gpt":0.2670039921151044,"score_spread":0.2285691858696297,"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."}}