{"id":"W4411726252","doi":"10.1109/iscas56072.2025.11043352","title":"Dynamic Spatial Filtering with Residual Spectral Mapping for Lightweight Multichannel Speech Enhancement","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Residual; Speech enhancement; Speech recognition; Artificial intelligence; Algorithm; Noise reduction","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005792712,0.0009010874,0.0005142846,0.0004739594,0.000163902,0.000379091,0.0007283225,0.0005298582,0.001810521],"category_scores_gemma":[0.0007020349,0.0002327944,0.0006980142,0.0002724103,0.0002501825,0.0007510515,0.0005786614,0.0007388112,0.001470732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001691285,"about_ca_system_score_gemma":0.0003587621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001001298,"about_ca_topic_score_gemma":0.002875403,"domain_scores_codex":[0.9997589,0.00004983246,0.00001444913,0.0000693207,0.00008393991,0.00002366781],"domain_scores_gemma":[0.9996943,0.0001143637,0.00002399399,0.00007122919,0.00008063922,0.00001544169],"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":[0.0004700283,0.0001338845,0.0005914391,0.0001935152,0.0001158216,0.0001430086,0.00006674905,0.04420293,0.2158401,0.002902952,0.002835853,0.7325038],"study_design_scores_gemma":[0.00003799783,0.0003031658,0.001129627,0.0000258525,0.0001060686,0.0005536536,0.00003919638,0.8237903,0.1559527,0.003117663,0.01490394,0.0000398793],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01536295,0.001124443,0.9803608,0.0001065452,0.000107613,0.00003563233,0.0001198156,0.001483422,0.001298836],"genre_scores_gemma":[0.2018606,0.001154292,0.788779,0.0002301956,0.0001576681,0.00008567504,0.0006882867,0.000259433,0.006784988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001810521,"threshold_uncertainty_score":0.006056786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009850163070860217,"score_gpt":0.2466236882901707,"score_spread":0.2367735252193105,"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."}}