{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:14:53Z","timestamp":1783437293909,"version":"3.54.6"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447464","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11561-11565","source":"Crossref","is-referenced-by-count":36,"title":["SELM: Speech Enhancement using Discrete Tokens and Language Models"],"prefix":"10.1109","author":[{"given":"Ziqian","family":"Wang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinfa","family":"Zhu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"YuanJun","family":"Lv","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Jiang","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoqing","family":"Zhao","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Co., Ltd."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1495"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414060"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3207349"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2979603"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3294692"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10653"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023356"},{"key":"ref12","first-page":"1336","article-title":"On generative spoken language modeling from raw audio","volume":"9","author":"Lakhotia","year":"2021","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref13","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref14","article-title":"Speechgen: Unlocking the generative power of speech language models with prompts","author":"Wu","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419418"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2069"},{"key":"ref17","article-title":"Voicebox: Text-guided multilingual universal speech generation at scale","author":"Le","year":"2023"},{"key":"ref18","article-title":"Vec-tok speech: Speech vectorization and tokenization for neural speech generation","author":"Zhu","year":"2023"},{"key":"ref19","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proceedings of the fifth Berkeley symposium on mathematical statistics and probability","volume":"1","author":"MacQueen"},{"key":"ref20","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NIPS","author":"Kong"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref22","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref23","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref24","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","volume":"33","author":"Brown"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref29","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1609"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref35","article-title":"Nu-gan: High resolution neural upsampling with gan","author":"Kumar","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094858"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447464.pdf?arnumber=10447464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:33:46Z","timestamp":1722573226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447464","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}