{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:46:16Z","timestamp":1784216776420,"version":"3.55.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413386","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6918-6922","source":"Crossref","is-referenced-by-count":57,"title":["The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods"],"prefix":"10.1109","author":[{"given":"Xian","family":"Shi","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Yu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhou","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,SpeechLab,Department of Computer Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Liang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiangze","family":"Feng","sequence":"additional","affiliation":[{"name":"Datatang (Beijing) Technology Co., LTD,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daliang","family":"Wang","sequence":"additional","affiliation":[{"name":"Datatang (Beijing) Technology Co., LTD,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,SpeechLab,Department of Computer Science and Engineering,China"}],"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,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","article-title":"Aispeech-sjtu asr system for the accented english speech recognition challenge","author":"tan","year":"2021","journal-title":"Proc ICASSP 2021"},{"key":"ref31","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607975"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/AUTOID.2005.10"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INDICON47234.2019.9030363"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0045"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053300"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2122"},{"key":"ref16","article-title":"Comparison of discriminative input and output transformations for speaker adaptation in the hybrid nn\/hmm systems","author":"li","year":"0","journal-title":"INTERSPEECH 2010"},{"key":"ref17","article-title":"Multi-accent adaptation based on gate mechanism","author":"zhu","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462663"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053098"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref4","article-title":"Exploiting spectral augmentation for code-switched spoken language identification","author":"rangan","year":"2020"},{"key":"ref27","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.05.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SPICES.2017.8091332"},{"key":"ref29","article-title":"Lite transformer with long-short range attention","author":"wu","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.047"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref2","article-title":"Speaker accent recognition through statistical descriptors of melbands spectral energy and neural network model","author":"ma","year":"2012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2489558"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683705"},{"key":"ref22","first-page":"6532","article-title":"Open-source Multi-speaker Corpora of the English Accents in the British Isles","author":"demirsahin","year":"2020","journal-title":"Proceedings of The 12th LREC"},{"key":"ref21","article-title":"Improving deep neural networks based multi-accent mandarin speech recognition using i-vectors and accent-specific top layer","author":"chen","year":"2015","journal-title":"InterSpeech"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref23","article-title":"Openslr68: Magicdata mandarin chinese read speech corpus","year":"0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref25","article-title":"Aispeech-sjtu accent identification system for the accented english speech recognition challenge","author":"huang","year":"0","journal-title":"Proc ICASSP 2021"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413386.pdf?arnumber=9413386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:17:59Z","timestamp":1659485879000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413386\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413386","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}