{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T17:17:49Z","timestamp":1770830269475,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3389630","type":"journal-article","created":{"date-parts":[[2024,4,16]],"date-time":"2024-04-16T17:28:20Z","timestamp":1713288500000},"page":"2432-2444","source":"Crossref","is-referenced-by-count":5,"title":["Conversational Speech Recognition by Learning Audio-Textual Cross-Modal Contextual Representation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1480-9009","authenticated-orcid":false,"given":"Kun","family":"Wei","sequence":"first","affiliation":[{"name":"Audio, Speech and Language Processing Group, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7617-9041","authenticated-orcid":false,"given":"Bei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3761-1684","authenticated-orcid":false,"given":"Hang","family":"Lv","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Lu","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Company, Ltd., Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4549-6372","authenticated-orcid":false,"given":"Ning","family":"Jiang","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Company, Ltd., Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-0823","authenticated-orcid":false,"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.444"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2756440"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-3173"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424228"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746884"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639044"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2928"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1643"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094687"},{"key":"ref18","first-page":"460","article-title":"Large-context automatic speech recognition based on RNN transducer","volume-title":"Proc. IEEE Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Kojima","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096900"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-697"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-552"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10066"},{"key":"ref23","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref25","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10326"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref28","article-title":"Searching for activation functions","author":"Ramachandran","year":"2018","journal-title":"Proc. 6th Int. Conf. Learn. Representations"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref30","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dauphin","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095508"},{"key":"ref32","article-title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pre-training","author":"Bapna","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3379877"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-791"},{"key":"ref35","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref40","first-page":"1416","article-title":"Efficient self-supervised learning with contextualized target representations for vision, speech and language","author":"Baevski","year":"2023","journal-title":"Proc. Int. Conf. Mach. Learn."},{"key":"ref41","article-title":"TESSP: Text-enhanced self-supervised speech pre-training","author":"Yao","year":"2022"},{"key":"ref42","article-title":"Opt: Omni-perception pre-trainer for cross-modal understanding and generation","author":"Liu","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11985"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/727"},{"key":"ref45","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-729"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/11939993_73"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414928"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1296"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10502286.pdf?arnumber=10502286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,3]],"date-time":"2024-05-03T18:59:38Z","timestamp":1714762778000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10502286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3389630","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}