{"id":"W3131443528","doi":"","title":"An Integrated CNN-GRU Framework for Complex Ratio Mask Estimation in Speech Enhancement","year":2020,"lang":"en","type":"article","venue":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Concordia University","funders":"","keywords":"Computer science; Convolutional neural network; Speech recognition; Speech enhancement; Convolution (computer science); Artificial intelligence; Deep learning; Residual; Recurrent neural network; Artificial neural network; Pattern recognition (psychology); Convergence (economics); 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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004780145,0.0001974015,0.000245991,0.0001300247,0.000305358,0.001253461,0.0002344573,0.0001552932,0.00003475628],"category_scores_gemma":[0.0002432878,0.0001876053,0.00002530495,0.000505978,0.00003685509,0.006770246,0.00004391756,0.0002106201,0.00001437877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008684392,"about_ca_system_score_gemma":0.0002031655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001167098,"about_ca_topic_score_gemma":0.000005703484,"domain_scores_codex":[0.998486,0.00005611663,0.0005283073,0.0002883878,0.0003432271,0.0002979466],"domain_scores_gemma":[0.9986855,0.00009089709,0.0004598864,0.00008722111,0.0005186173,0.0001578286],"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":[0.00006312427,0.00005299556,0.003601828,0.0001626759,0.0000148491,6.728975e-7,0.01399573,0.0001114824,0.001038364,0.008686716,0.0005865782,0.971685],"study_design_scores_gemma":[0.001111944,0.0004376693,0.005368985,0.000220613,0.00001767139,0.000002182055,0.01298059,0.9454526,0.01627284,0.01130315,0.006289966,0.0005417682],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01422958,0.00005867446,0.9790894,0.005172167,0.00005468214,0.000303462,0.00002395968,0.0001312303,0.0009368229],"genre_scores_gemma":[0.8950099,0.00003071919,0.1034705,0.00122043,0.00003624636,0.00004027888,0.0001401903,0.000005075765,0.0000466654],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9711432,"threshold_uncertainty_score":0.9997833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01897797286456646,"score_gpt":0.2582240652898218,"score_spread":0.2392460924252553,"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."}}