{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:31:00Z","timestamp":1769733060772,"version":"3.49.0"},"reference-count":23,"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\/icassp39728.2021.9414082","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7253-7257","source":"Crossref","is-referenced-by-count":17,"title":["An End-to-End Speech Accent Recognition Method Based on Hybrid CTC\/Attention Transformer ASR"],"prefix":"10.1109","author":[{"given":"Qiang","family":"Gao","sequence":"first","affiliation":[{"name":"NetEase Youdao,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiwei","family":"Wu","sequence":"additional","affiliation":[{"name":"NetEase Youdao,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanqing","family":"Sun","sequence":"additional","affiliation":[{"name":"NetEase Youdao,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitao","family":"Duan","sequence":"additional","affiliation":[{"name":"NetEase Youdao,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268945"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462180"},{"key":"ref12","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref14","article-title":"Bridging nonlinearities and stochastic regularizers with gaussian error linear units","author":"hendrycks","year":"2016","journal-title":"CoRR"},{"key":"ref15","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref19","article-title":"Neural machine translation of rare words with subword units","author":"sennrich","year":"2015","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639089"},{"key":"ref3","article-title":"The accented english speech recognition challenge 2020: open datasets, tracks, baselines, results and methods","author":"shi","year":"2020"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"745","DOI":"10.21437\/Interspeech.2011-285","article-title":"Dialect and accent recognition using phonetic-segmentation supervectors","author":"biadsy","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-015-1019-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.033"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101030"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1667"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2737"},{"key":"ref9","article-title":"A new approach to accent recognition and conversion for mandarin chinese","author":"ai","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023189"}],"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\/09414082.pdf?arnumber=9414082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:31:47Z","timestamp":1672129907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414082","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}