{"id":"W4408353488","doi":"10.1109/icassp49660.2025.10890758","title":"Design and Optimization of Superdirective Beamforming and Post-Filtering for Speech Enhancement","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Montréal","funders":"Research and Development","keywords":"Beamforming; Speech enhancement; Computer science; Speech recognition; Acoustics; Artificial intelligence; Noise reduction; 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":[0.0001625241,0.0000534482,0.0000825862,0.00007045485,0.00007362817,0.00006353911,0.00008257893,0.0000184031,0.000001637762],"category_scores_gemma":[0.00003046496,0.00004740371,0.000009161835,0.000111766,0.00001909157,0.0003841018,0.00008989804,0.00001665557,6.452421e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001173378,"about_ca_system_score_gemma":0.00003161272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005894623,"about_ca_topic_score_gemma":9.544782e-7,"domain_scores_codex":[0.9995925,0.000006398775,0.0001000945,0.0001612635,0.00004695681,0.00009281124],"domain_scores_gemma":[0.9997318,0.0000662318,0.00002861461,0.00007217602,0.00008309841,0.00001803066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002129164,0.00002119806,0.00008430794,0.0001151253,0.00002165748,4.464416e-7,0.0006132006,0.004392687,0.3538224,0.001259974,0.00002589893,0.6396218],"study_design_scores_gemma":[0.0001836679,0.00006703765,0.0000448598,0.00004693571,0.000004165068,0.000002248114,0.00005003235,0.1291424,0.869535,0.0008541327,0.00002191287,0.00004760448],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01781136,0.0001601916,0.9809561,0.0002600412,0.00005554175,0.0001890424,1.802303e-7,0.00002586603,0.0005416398],"genre_scores_gemma":[0.07873762,0.00002566262,0.9208899,0.0001208477,0.000005076269,0.00001048169,4.898481e-7,0.000001931034,0.0002079818],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6395742,"threshold_uncertainty_score":0.1933067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01271446269298552,"score_gpt":0.2541525022079974,"score_spread":0.2414380395150119,"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."}}