{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T09:07:51Z","timestamp":1768295271639,"version":"3.49.0"},"reference-count":54,"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.2023.3332542","type":"journal-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:33:23Z","timestamp":1699904003000},"page":"459-470","source":"Crossref","is-referenced-by-count":13,"title":["Decoupling and Interacting Multi-Task Learning Network for Joint Speech and Accent Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2145-4077","authenticated-orcid":false,"given":"Qijie","family":"Shao","sequence":"first","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2388-5935","authenticated-orcid":false,"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6845-9201","authenticated-orcid":false,"given":"Jinghao","family":"Yan","sequence":"additional","affiliation":[{"name":"Tencent Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4537-6288","authenticated-orcid":false,"given":"Pengfei","family":"Hu","sequence":"additional","affiliation":[{"name":"Tencent Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-0823","authenticated-orcid":false,"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414292"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324920000091"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-495"},{"key":"ref53","first-page":"26","article-title":"Pronunciation problems of Chinese learners of English","volume":"30","author":"han","year":"2013","journal-title":"ORTESOL Journal"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1051\/shsconf\/20207702003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1048"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2235"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2742"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414082"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1186"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA46868.2019.9041230"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref46","article-title":"Arpabet and the timit alphabet","author":"klautau","year":"2001"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10037884"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414428"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2639323"},{"key":"ref43","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","article-title":"KeSpeech: An open source speech dataset of Mandarin and its eight subdialects","author":"tang","year":"0","journal-title":"Proc Thirty-fifth Conf Neural Inf Process Syst Datasets Benchmarks Track"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1495"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1864"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413386"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3198546"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095860"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038197"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383506"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-334"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953071"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461361"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04221-9_19"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1075"},{"key":"ref30","first-page":"12449","article-title":"Wav2Vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"0","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/B:IJST.0000017014.52972.1d"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203348802"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688053"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1107"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414291"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/s21186258"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462663"},{"key":"ref22","first-page":"297","article-title":"Dialect-aware modeling for end-to-end Japanese dialect speech recognition","author":"imaizumi","year":"0","journal-title":"Proc Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10444"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462557"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2122"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10739"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10316571.pdf?arnumber=10316571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T23:17:47Z","timestamp":1701299867000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10316571\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3332542","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}