{"id":"W3138320152","doi":"10.48550/arxiv.2103.09963","title":"TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Encoder; Computer science; Transformer; Speech recognition; Artificial neural network; Benchmark (surveying); Time domain; Pattern recognition (psychology); Artificial intelligence; Voltage; Computer vision; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004341222,0.0007789836,0.0004356717,0.00027961,0.0001703301,0.0004563516,0.001169985,0.0007128705,0.002664563],"category_scores_gemma":[0.0007792807,0.0002537854,0.0006195242,0.0003033717,0.0003317372,0.001018768,0.0007276575,0.001057611,0.001281072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000387018,"about_ca_system_score_gemma":0.0005427522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003013632,"about_ca_topic_score_gemma":0.006063059,"domain_scores_codex":[0.9998329,0.00002688638,0.00001074238,0.00004587684,0.00005609345,0.00002744201],"domain_scores_gemma":[0.9998069,0.00006564175,0.0000154858,0.00002689281,0.00007073706,0.00001428453],"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":[0.0006105911,0.0001868409,0.001169714,0.0002554227,0.0001803169,0.0002581805,0.0001069191,0.2096173,0.100617,0.007891367,0.005220952,0.6738853],"study_design_scores_gemma":[0.00001103832,0.0001047146,0.000239634,0.0000120773,0.00003752409,0.0001171756,0.00001239228,0.9720477,0.022678,0.002424843,0.002302097,0.00001267254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01869331,0.0007697108,0.9760006,0.0001209596,0.0001540269,0.00005264936,0.0001388071,0.001566866,0.002503039],"genre_scores_gemma":[0.5769465,0.001189022,0.4058576,0.0004337065,0.00009130625,0.000151673,0.001101034,0.0002585544,0.01397055],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003013632,"threshold_uncertainty_score":0.008913875,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04695501557876084,"score_gpt":0.2056079478297167,"score_spread":0.1586529322509558,"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."}}