{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:25:14Z","timestamp":1777656314651,"version":"3.51.4"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747760","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"7802-7806","source":"Crossref","is-referenced-by-count":15,"title":["Optimizing Alignment of Speech and Language Latent Spaces for End-To-End Speech Recognition and Understanding"],"prefix":"10.1109","author":[{"given":"Wei","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Ren","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Qian","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Shi","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Department of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Zeng","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461361"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CISP-BMEI51763.2020.9263564"},{"key":"ref14","article-title":"Phoneme-bert: Joint language modelling of phoneme sequence and asr transcript","author":"sundararaman","year":"2021","journal-title":"arXiv preprint arXiv 2102 05988"},{"key":"ref15","article-title":"Code-switching pre-training for neural machine translation","author":"yang","year":"2020","journal-title":"arXiv preprint arXiv 2009 08003"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.210"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref18","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref3","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"arXiv preprint arXiv 1506 07310"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2456"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415058"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053281"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003873"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6452"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref21","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref25","article-title":"Se-mantic mask for transformer based end-to-end speech recognition","author":"wang","year":"2019","journal-title":"arXiv preprint arXiv 1912 03010"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747760.pdf?arnumber=9747760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:09:57Z","timestamp":1661184597000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747760","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}