{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T20:23:21Z","timestamp":1779913401747,"version":"3.53.1"},"reference-count":33,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446365","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10201-10205","source":"Crossref","is-referenced-by-count":2,"title":["Accent-Specific Vector Quantization for Joint Unsupervised and Supervised Training in Accent Robust Speech Recognition"],"prefix":"10.1109","author":[{"given":"Li","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yijie","family":"Li","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd.,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongxing","family":"Xu","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd.,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Wei","sequence":"additional","affiliation":[{"name":"University of Texas at Dallas,Department of ECE,Richardson,TX,USA,75080"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhua","family":"Long","sequence":"additional","affiliation":[{"name":"Shanghai Normal University,Shanghai Engineering Research Center of Intelligent Education and Bigdata,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2361"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688251"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414471"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3198546"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2742"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2122"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414833"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1186"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096854"},{"key":"ref14","article-title":"Task agnostic and task specific self-supervised learning from speech with lebenchmark","volume-title":"Proc. NeurIPS","author":"Evain"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.634"},{"key":"ref16","article-title":"Continual-wav2vec2: an application of continual learning for self-supervised automatic speech recognition","author":"Kessler","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414227"},{"key":"ref18","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref19","first-page":"10937","article-title":"Unispeech: Unified speech representation learning with labeled and unlabeled data","volume-title":"Proc. ICML","author":"Wang"},{"key":"ref20","article-title":"Hybrid unsupervised and supervised multitask learning for speech recognition in low resource languages","volume-title":"Proc. Workshop on Machine Learning in Speech and Language Processing","author":"Raghavan"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746038"},{"key":"ref22","article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. ICML","author":"Graves"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414911"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1864"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683705"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","first-page":"4218","article-title":"Common Voice: A massively-multilingual speech corpus","volume-title":"Proc. LREC","author":"Ardila"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"}],"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\/10446365.pdf?arnumber=10446365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:13:08Z","timestamp":1722575588000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446365\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446365","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}