{"id":"W3161950572","doi":"10.1109/icassp39728.2021.9413740","title":"TSTNN: Two-Stage Transformer Based Neural Network for Speech Enhancement in the Time Domain","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Encoder; Computer science; Transformer; Speech recognition; Artificial neural network; Speech enhancement; Benchmark (surveying); Time domain; Pattern recognition (psychology); Artificial intelligence; Noise reduction; Computer vision; Engineering; Voltage","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":[0.0004237488,0.0007644268,0.00042886,0.0002779218,0.0001724434,0.0004374586,0.001147645,0.000685823,0.002585863],"category_scores_gemma":[0.0007355655,0.0002487665,0.0006060849,0.0002943489,0.0003158868,0.001005857,0.0006706838,0.001016861,0.001213773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003950901,"about_ca_system_score_gemma":0.0005464238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003240319,"about_ca_topic_score_gemma":0.00672214,"domain_scores_codex":[0.9998388,0.00002524215,0.00001059738,0.00004284329,0.00005558183,0.00002695138],"domain_scores_gemma":[0.9998111,0.00006245932,0.00001535147,0.0000244222,0.00007265314,0.00001395695],"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":[0.0005933584,0.0001845175,0.001209109,0.000261544,0.0001841584,0.0002604339,0.0001033545,0.201522,0.1057181,0.00706423,0.005248894,0.6776503],"study_design_scores_gemma":[0.00001142191,0.000113482,0.0002616358,0.00001278372,0.00004084255,0.0001239461,0.00001306992,0.9702637,0.02464557,0.002094724,0.002404926,0.00001392377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02064491,0.0008672901,0.9736603,0.0001261087,0.0001689777,0.00005672927,0.0001447694,0.001654707,0.002676237],"genre_scores_gemma":[0.59358,0.001263063,0.3891406,0.000442229,0.00008910622,0.000152467,0.001092741,0.0002488862,0.01399084],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003240319,"threshold_uncertainty_score":0.008650541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01613232171435938,"score_gpt":0.2649973294156781,"score_spread":0.2488650077013187,"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."}}