{"id":"W4387697016","doi":"10.1109/raiic59453.2023.10281019","title":"Efficient Monaural Speech Enhancement using Spectrum Attention Fusion","year":2023,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Speech enhancement; Speech recognition; Transformer; Monaural; Speech processing; Linear predictive coding; Speech coding; Fuse (electrical); Artificial intelligence; Noise reduction; Engineering","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":[0.0002592056,0.0001067735,0.00009441013,0.0001603454,0.0002127508,0.00017466,0.0003339939,0.00003165604,0.00006949389],"category_scores_gemma":[0.000009977337,0.00009114947,0.00005459894,0.0008903843,0.00001600606,0.0001428643,0.0003015232,0.00006593039,0.000557646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007104917,"about_ca_system_score_gemma":0.00003857416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003438347,"about_ca_topic_score_gemma":0.000005128387,"domain_scores_codex":[0.9987197,0.00001830029,0.0001751884,0.0003427463,0.000374843,0.0003692478],"domain_scores_gemma":[0.9995613,0.00001480118,0.00005903011,0.000263821,0.00003270809,0.00006838357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006046612,0.0001021995,0.001307236,0.00003133485,0.00001171218,0.00007894386,0.0002437673,0.004356807,0.8520823,0.001476279,0.001089533,0.1392139],"study_design_scores_gemma":[0.0001856895,0.0000342624,0.002925251,0.00003529123,0.000002910234,0.00001701725,0.00003610158,0.5574647,0.4378776,0.001065925,0.0001977064,0.0001575344],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6246368,0.00002145073,0.3720804,0.0007865643,0.0003809045,0.0000718741,1.579772e-7,0.0002924193,0.001729512],"genre_scores_gemma":[0.9266087,0.000006440569,0.07122929,0.0001648438,0.00009914519,0.000002944972,0.000002753229,0.000007503727,0.001878396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5531079,"threshold_uncertainty_score":0.7167597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02455344076314992,"score_gpt":0.2717264962069612,"score_spread":0.2471730554438113,"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."}}