{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:31:05Z","timestamp":1772119865910,"version":"3.50.1"},"reference-count":24,"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\/icassp39728.2021.9415017","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"7303-7307","source":"Crossref","is-referenced-by-count":16,"title":["A Sequential Contrastive Learning Framework for Robust Dysarthric Speech Recognition"],"prefix":"10.1109","author":[{"given":"Lidan","family":"Wu","sequence":"first","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daoming","family":"Zong","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiliang","family":"Sun","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhao","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683091"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054694"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1751"},{"key":"ref14","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"949","DOI":"10.21437\/Interspeech.2017-1296","article-title":"Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM","author":"hori","year":"2017","journal-title":"InterSpeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018497"},{"key":"ref17","first-page":"15535","article-title":"Learning representations by maximizing mutual information across views","author":"bachman","year":"2019","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2250"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1754"},{"key":"ref6","first-page":"72","article-title":"State- transition interpolation and MAP adaptation for HMM- based dysarthric speech recognition","author":"sharma","year":"2010","journal-title":"NAACL"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1206"},{"key":"ref8","first-page":"5884","article-title":"Speech-Transformer: A no-recurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"ICASSP"},{"key":"ref7","first-page":"206","article-title":"Exploring neural transducers for end-to-end speech recognition","author":"battenberg","year":"2017","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref2","first-page":"1","article-title":"Deep Learning of Articulatory-Based Representations and Applications for Improving Dysarthric Speech Recognition","author":"xiong","year":"2018","journal-title":"IEEE Speech Communication"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1318"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2018.2802914"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-011-9145-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref23","first-page":"6109","article-title":"Dysarthric speech recognition with lattice-free MMI","author":"hermann","year":"2020","journal-title":"ICASSP"}],"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\/09415017.pdf?arnumber=9415017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T20:18:47Z","timestamp":1659471527000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9415017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9415017","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}