{"id":"W4312069169","doi":"10.1109/tencon55691.2022.9977891","title":"DBAUNet: Dual-branch attention U-Net for time-domain speech enhancement","year":2022,"lang":"en","type":"article","venue":"TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Speech enhancement; Encoder; Speech recognition; Dual (grammatical number); Benchmark (surveying); Block (permutation group theory); Artificial intelligence; Waveform; Channel (broadcasting); Speech coding; Pattern recognition (psychology); Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005217307,0.00120926,0.0008104811,0.0007452579,0.0003160233,0.0005569511,0.001482671,0.0008145657,0.004052809],"category_scores_gemma":[0.0007431857,0.000331392,0.0006453869,0.0004974263,0.0003449546,0.0010507,0.00109189,0.00110259,0.001701099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000553731,"about_ca_system_score_gemma":0.000697317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006478539,"about_ca_topic_score_gemma":0.01174368,"domain_scores_codex":[0.9998098,0.00003038095,0.00001013847,0.00005848234,0.00005191596,0.00003921776],"domain_scores_gemma":[0.9997951,0.00007865688,0.00001398174,0.00003076924,0.00006177618,0.00001972475],"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":[0.0006882179,0.0002227018,0.0008607401,0.0001559095,0.0001261991,0.0002099509,0.00005173467,0.0841224,0.02944909,0.004051902,0.01183884,0.8682224],"study_design_scores_gemma":[0.00003059988,0.0001582136,0.0004479552,0.0000190851,0.00005079562,0.0001448265,0.00001894108,0.9669359,0.02424977,0.002266433,0.005660336,0.00001720355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03867529,0.003766465,0.9382107,0.0002322335,0.0003451945,0.000180269,0.0004717133,0.0105437,0.007574355],"genre_scores_gemma":[0.4993936,0.00167972,0.4674937,0.0008276792,0.0001841318,0.0002666668,0.002870221,0.0005210454,0.02676335],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006478539,"threshold_uncertainty_score":0.01355803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02485301095581643,"score_gpt":0.2543724736206642,"score_spread":0.2295194626648478,"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."}}