{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:33:19Z","timestamp":1781584399829,"version":"3.54.5"},"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.2024.3379877","type":"journal-article","created":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T18:30:46Z","timestamp":1710959446000},"page":"2177-2187","source":"Crossref","is-referenced-by-count":31,"title":["SpeechLM: Enhanced Speech Pre-Training With Unpaired Textual Data"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0110-1543","authenticated-orcid":false,"given":"Ziqiang","family":"Zhang","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3082-6052","authenticated-orcid":false,"given":"Sanyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1919-4943","authenticated-orcid":false,"given":"Long","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5715-3011","authenticated-orcid":false,"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Ren","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuoyuan","family":"Yao","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Gong","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0859-2827","authenticated-orcid":false,"given":"Lirong","family":"Dai","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1089-9748","authenticated-orcid":false,"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Furu","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref2","first-page":"13063","article-title":"Unified language model pre-training for natural language understanding and generation","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Dong","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref4","first-page":"3451","article-title":"HuBERT: Self-supervised speech representation learning by masked prediction of hidden units","volume-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process.","volume":"29","author":"Hsu","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandl.2016.08.004"},{"key":"ref6","article-title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pre-training","author":"Bapna","year":"2021"},{"key":"ref7","article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","author":"Bapna","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref11","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-936"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414558"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414900"},{"key":"ref17","first-page":"5723","article-title":"SpeechT5: Unified-modal encoder-decoder pre-training for spoken language processing","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","author":"Ao","year":"2022"},{"key":"ref18","first-page":"1488","article-title":"Unified speech-text pre-training for speech translation and recognition","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","author":"Tang","year":"2022"},{"key":"ref19","first-page":"1663","article-title":"SpeechUT: Bridging speech and text with hidden-unit for encoder-decoder based speech-text pre-training","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Zhang","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022774"},{"key":"ref21","first-page":"5504","article-title":"Mu $^{2}$ SLAM: Multitask, multilingual speech and language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Cheng","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747760"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"ref27","article-title":"The kaldi speech recognition toolkit","author":"Povey","year":"2011"},{"key":"ref28","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref32","first-page":"4211","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Conf. Lang. Resour. Eval.","author":"Ardila","year":"2020"},{"key":"ref33","first-page":"27826","article-title":"Unsupervised speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447751"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref37","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":"ref38","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10114"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2021-1912","article-title":"Large-scale self- and semi-supervised learning for speech translation","author":"Wang","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-349"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3095662"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053176"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414027"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"issue":"11","key":"ref52","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10476749.pdf?arnumber=10476749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T05:19:00Z","timestamp":1712639940000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10476749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3379877","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}