{"id":"W4312095841","doi":"10.23919/apsipaasc55919.2022.9980330","title":"SE-Mixer: Towards an Efficient Attention-free Neural Network for Speech Enhancement","year":2022,"lang":"en","type":"article","venue":"2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Benchmark (surveying); Speech recognition; Convolution (computer science); Encoder; Speech enhancement; Perceptron; Artificial neural network; Artificial intelligence; Multilayer perceptron; Convolutional neural network; Pattern recognition (psychology); 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001456923,0.0002765467,0.0003117835,0.0001897243,0.001818063,0.001323061,0.0005578092,0.0001046563,0.000150185],"category_scores_gemma":[0.0000934163,0.0002770364,0.00007822538,0.0006279604,0.0000495418,0.003961112,0.0003644481,0.000324881,0.000007366161],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002126169,"about_ca_system_score_gemma":0.0003064102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002529186,"about_ca_topic_score_gemma":0.000008628454,"domain_scores_codex":[0.997295,0.0001298103,0.0006344815,0.0004336976,0.0009375708,0.00056941],"domain_scores_gemma":[0.9981607,0.00006610673,0.0007065121,0.0002275109,0.0006444678,0.0001947476],"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":[0.0001165538,0.000188051,0.003569042,0.0001740011,0.00006385685,0.000002394609,0.008602921,0.001470288,0.0004042382,0.006127428,0.0130688,0.9662125],"study_design_scores_gemma":[0.004225766,0.001581762,0.01034502,0.0001431727,0.0001219029,0.00003989083,0.03556002,0.8000143,0.003859966,0.009021459,0.133342,0.001744714],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4065744,0.001761212,0.5503272,0.01647932,0.002476454,0.002272637,0.0006588633,0.0009689547,0.01848094],"genre_scores_gemma":[0.9879769,0.00004644166,0.008729818,0.0008866664,0.0001832162,0.0002493856,0.0003253536,0.00001351338,0.001588723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9644677,"threshold_uncertainty_score":0.9999682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01192480049890464,"score_gpt":0.2353018325490443,"score_spread":0.2233770320501397,"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."}}