{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007178658,0.0003318381,0.0003539839,0.000135887,0.0002251368,0.0003352663,0.001973913,0.00016381,0.00008047587],"category_scores_gemma":[0.00001338906,0.0003080459,0.0002864014,0.0008176295,0.00007049499,0.0003587663,0.0002847384,0.0005169935,0.00001865244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001549466,"about_ca_system_score_gemma":0.0003260655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005128793,"about_ca_topic_score_gemma":0.000145907,"domain_scores_codex":[0.9977653,0.0001994334,0.0002532006,0.001013336,0.0001552116,0.0006134973],"domain_scores_gemma":[0.9985204,0.0002042285,0.0001798312,0.0009044381,0.00009773739,0.00009337183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002182134,0.0005063413,0.001542125,0.0004491088,0.0001408305,0.001950149,0.00171065,0.9631887,0.002793401,0.01051636,0.001284765,0.01569936],"study_design_scores_gemma":[0.002868631,0.000165751,0.0003459182,0.0003775024,0.00008186652,0.00001023122,0.0003359462,0.9554856,0.01770728,0.01830666,0.003260039,0.001054624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2982749,0.0001040816,0.6985269,0.000591816,0.0003083219,0.0005474308,0.000008364986,0.00006740882,0.001570854],"genre_scores_gemma":[0.958659,0.00002573144,0.03876449,0.001276357,0.0001699373,0.000007963324,0.00005162018,0.00001916957,0.001025707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6603842,"threshold_uncertainty_score":0.9999372,"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."}}