{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T11:27:25Z","timestamp":1768735645964,"version":"3.49.0"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2023.3332545","type":"journal-article","created":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T19:34:45Z","timestamp":1702064085000},"page":"1145-1156","source":"Crossref","is-referenced-by-count":12,"title":["Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0696-6434","authenticated-orcid":false,"given":"Yuchen","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4181-9285","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1196-7781","authenticated-orcid":false,"given":"Qiushi","family":"Zhu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6257-7399","authenticated-orcid":false,"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref2","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Graves","year":"2014"},{"key":"ref3","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Chorowski","year":"2015"},{"key":"ref4","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163930"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-491"},{"key":"ref11","article-title":"Improving transformer-based speech recognition using unsupervised pre-training","author":"Jiang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2638"},{"key":"ref14","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.834466"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(94)00059-J"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683453"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854127"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3064421"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854051"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178797"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472778"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1270"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2528171"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1242"},{"key":"ref36","first-page":"497","article-title":"Multitask-based joint learning approach to robust ASR for radio communication speech","volume-title":"Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Ma","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414027"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-318"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2383"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2946789"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746314"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-101"},{"key":"ref43","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chiu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref46","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref49","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref50","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen","year":"2017"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746929"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747379"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3275033"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref56","article-title":"Discretization and re-synthesis: An alternative method to solve the cocktail party problem","author":"Shi","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10084"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref59","first-page":"2835","article-title":"High fidelity neural audio compression","volume-title":"Trans. Mach. Learn. Res.","author":"Dfossez","year":"2023"},{"key":"ref60","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Oord","year":"2017"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref62","first-page":"30599","article-title":"Towards robust blind face restoration with codebook lookup transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhou","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3142999"},{"key":"ref64","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref65","first-page":"1","article-title":"Categorical reparameterization with Gumbel-Softmax","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jang","year":"2017"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/asru.2013.6707723"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref69","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref71","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei","year":"2016"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref73","first-page":"49","article-title":"The RWTH\/UPB\/FORTH system combination for the 4th chime challenge evaluation","volume-title":"Proc. CHiME-4 Workshop","author":"Menne","year":"2016"},{"key":"ref74","first-page":"36","article-title":"The USTC-iFlytek system for chime-4 challenge","volume-title":"Proc. CHiME","volume":"4","author":"Du","year":"2016"},{"key":"ref75","first-page":"49","article-title":"The RWTH\/UPB\/FORTH system combination for the 4th chime challenge evaluation","volume-title":"Proc. CHiME-4 Workshop","author":"Menne","year":"2016"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746220"},{"key":"ref77","article-title":"Data augmentation based consistency contrastive pre-training for automatic speech recognition","author":"Gao","year":"2021"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095373"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10349911.pdf?arnumber=10349911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:35:41Z","timestamp":1706769341000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10349911\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3332545","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}