{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:36:39Z","timestamp":1780587399293,"version":"3.54.1"},"reference-count":48,"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"}],"funder":[{"DOI":"10.13039\/100016909","name":"Microsoft Research Asia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016909","id-type":"DOI","asserted-by":"publisher"}]}],"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.2024.3434425","type":"journal-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T19:44:47Z","timestamp":1722282287000},"page":"3709-3716","source":"Crossref","is-referenced-by-count":21,"title":["VioLA: Conditional Language Models for Speech Recognition, Synthesis, and Translation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2765-5889","authenticated-orcid":false,"given":"Tianrui","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Information Science and the Beijing Key Laboratory of Advanced Information Science and Network Technology, Beijing Jiaotong University, Beijing, 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 Aisa, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0110-1543","authenticated-orcid":false,"given":"Ziqiang","family":"Zhang","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"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Research Aisa, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Aisa, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yashesh","family":"Gaur","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3082-6052","authenticated-orcid":false,"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Corporation, Redmond, WA, USA"}],"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7810-5852","authenticated-orcid":false,"given":"Furu","family":"Wei","sequence":"additional","affiliation":[{"name":"Microsoft Research Aisa, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref2","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technologies, Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref5","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref6","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"issue":"1","key":"ref8","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref9","article-title":"Introducing chatGPT","year":"2022","journal-title":"OpenAI Blog"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref11","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref12","article-title":"High fidelity neural audio compression","volume-title":"Trans. Mach. Learn. Res.","author":"Dfossez","year":"2023"},{"key":"ref13","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6360"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860774"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1452"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref25","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref26","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6337"},{"key":"ref28","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref32","article-title":"SpeechNet: A universal modularized model for speech processing tasks","author":"Chen","year":"2021"},{"key":"ref33","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref35","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389703"},{"key":"ref37","article-title":"Boosting large language model for speech synthesis: An empirical study","author":"Hao","year":"2023"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"1715","DOI":"10.18653\/v1\/P16-1162","article-title":"Neural machine translation of rare words with subword units","volume-title":"Proc. 54th Annu. Meeting Assoc. Comput. Linguistics (Volume 1: Long Papers)","author":"Sennrich","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2826"},{"key":"ref41","article-title":"The emime bilingual database","author":"Wester","year":"2010"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref43","article-title":"End-to-end ASR: From supervised to semi-supervised learning with modern architectures","volume-title":"Proc. ICML 2020 Workshop Self-Supervision Audio Speech","author":"Synnaeve","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682586"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2382"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1007\/978-981-33-6162-1_8","article-title":"Oppos machine translation systems for WMT20","volume-title":"Proc. 5th Conf. Mach. Transl.","author":"Shi","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10613503.pdf?arnumber=10613503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T04:01:55Z","timestamp":1723348915000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10613503\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3434425","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}