{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:04:37Z","timestamp":1775228677046,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746169","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7867-7871","source":"Crossref","is-referenced-by-count":67,"title":["Speech Denoising in the Waveform Domain With Self-Attention"],"prefix":"10.1109","author":[{"given":"Zhifeng","family":"Kong","sequence":"first","affiliation":[{"name":"UCSD"}]},{"given":"Wei","family":"Ping","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Ambrish","family":"Dantrey","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Bryan","family":"Catanzaro","sequence":"additional","affiliation":[{"name":"NVIDIA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref33","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683799"},{"key":"ref30","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018"},{"key":"ref37","article-title":"Noisy speech database for training speech enhancement algorithms and tts models","author":"valentini-botinhao","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87589-3_28"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref40","article-title":"Subjective test methodology for evaluating speech communication systems that include noise suppression algorithm","year":"2003","journal-title":"ITU-T Recommendation"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178800"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-22482-4_11","article-title":"Speech enhancement with lstm recurrent neural networks and its application to noise-robust asr","author":"weninger","year":"2015","journal-title":"International Conference on Latent Variable Analysis and Signal Separation"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.06.002"},{"key":"ref14","article-title":"Speech denoising with deep feature losses","author":"germain","year":"2018"},{"key":"ref15","article-title":"Multi-objective learning and mask-based post-processing for deep neural network based speech enhancement","author":"xu","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414177"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2631"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3027"},{"key":"ref19","article-title":"Complex ratio masking for monaural speech separation","author":"williamson","year":"2015","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref28","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"ICLRE"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196643"},{"key":"ref27","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"MICCAI"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1586","DOI":"10.1109\/PROC.1979.11540","article-title":"Enhancement and band-width compression of noisy speech","volume":"67","author":"lim","year":"1979","journal-title":"Proceedings of the IEEE"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326090"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"ref7","article-title":"A regression approach to speech enhancement based on deep neural networks","author":"xu","year":"2014","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref9","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","author":"fu","year":"2019","journal-title":"ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781420015836"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"Segan: Speech enhancement generative adversarial network","author":"pascual","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172555"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1567"},{"key":"ref26","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref25","article-title":"Perceptual evaluation of speech quality (pesq): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","year":"2001","journal-title":"ITU-T Rec P 862"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746169.pdf?arnumber=9746169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:22:59Z","timestamp":1727061779000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746169","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}