{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T07:02:19Z","timestamp":1763535739890,"version":"3.37.3"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976236"],"award-info":[{"award-number":["61976236"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MUC 111 Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3024218","type":"journal-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T20:52:24Z","timestamp":1600203144000},"page":"169160-169168","source":"Crossref","is-referenced-by-count":11,"title":["WaveNet With Cross-Attention for Audiovisual Speech Recognition"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8476-888X","authenticated-orcid":false,"given":"Hui","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7831-5721","authenticated-orcid":false,"given":"Fei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4007-7016","authenticated-orcid":false,"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Licheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/AVSP.2017-8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1301"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462439"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472088"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2815268"},{"key":"ref28","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/34.927467"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543246"},{"journal-title":"Github Repository","year":"2016","key":"ref27"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1327261"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2001.1237849"},{"key":"ref8","article-title":"Neural speech recognizer: Acoustic-to-Word LSTM model for large vocabulary speech recognition","author":"soltau","year":"2016","journal-title":"arXiv 1610 09975"},{"key":"ref7","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015","journal-title":"arXiv 1507 06947"},{"key":"ref2","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref1","article-title":"Modality attention for End-to-End audio-visual speech recognition","author":"zhou","year":"2018","journal-title":"arXiv 1811 05250"},{"key":"ref9","article-title":"The microsoft 2017 conversational speech recognition system","author":"xiong","year":"2017","journal-title":"arXiv 1708 06073"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-799"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2019.05636"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref23","article-title":"Pixel recurrent neural networks","author":"van den oord","year":"2016","journal-title":"arXiv 1601 06759"},{"journal-title":"Speech-to-Text-Wavenet End-to-End Sentence Level Chinese Speech Recognition Using Deepmind’s Wavenet","year":"2020","author":"xu","key":"ref26"},{"key":"ref25","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume":"32","author":"graves","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09197622.pdf?arnumber=9197622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:56Z","timestamp":1639770956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3024218","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}