{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:50:04Z","timestamp":1776883804703,"version":"3.51.2"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889325","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Large Language Models Are Efficient Learners as Zero-Shot Speech Translators"],"prefix":"10.1109","author":[{"given":"Chenxuan","family":"Liu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liping","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiwang","family":"Tang","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weitai","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxi","family":"Li","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sreyan","family":"Ghosh","sequence":"additional","affiliation":[{"name":"University of Maryland,College Park,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyi","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjia","family":"Yu","sequence":"additional","affiliation":[{"name":"China Jiliang University,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"8","key":"ref1","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Advances in neural information processing systems","volume":"33","author":"Brown"},{"key":"ref3","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref4","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref5","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref6","first-page":"22964","article-title":"What language model architecture and pretraining objective works best for zero-shot generalization?","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref7","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Advances in neural information processing systems","volume":"35","author":"Ouyang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446502"},{"key":"ref9","article-title":"It\u2019s never too late: Fusing acoustic information into large language models for automatic speech recognition","author":"Chen","year":"2024"},{"issue":"97","key":"ref10","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","article-title":"SeamlessM4T-massively multilingual & multimodal machine translation","author":"Barrault","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.789"},{"key":"ref13","article-title":"Can generative large language models perform ASR error correction?","author":"Ma","year":"2023"},{"key":"ref14","article-title":"Generative error correction for code-switching speech recognition using large language models","author":"Chen","year":"2023"},{"key":"ref15","article-title":"Hyporadise: An open baseline for generative speech recognition with large language models","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Chen"},{"key":"ref16","article-title":"Large language models are efficient learners of noise-robust speech recognition","author":"Hu","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1109"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446635"},{"key":"ref21","article-title":"A survey of chain of thought reasoning: Advances, frontiers and future","author":"Chu","year":"2023"},{"key":"ref22","article-title":"A systematic survey of prompt engineering in large language models: Techniques and applications","author":"Sahoo","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3690635"},{"key":"ref24","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021"},{"key":"ref25","article-title":"Chain-of-table: Evolving tables in the reasoning chain for table understanding","author":"Wang","year":"2024"},{"key":"ref26","article-title":"Buffer of thoughts: Thought-augmented reasoning with large language models","author":"Yang","year":"2024"},{"key":"ref27","article-title":"Automatic chain of thought prompting in large language models","author":"Zhang","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.73"},{"key":"ref29","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yao"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref34","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389673"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref38","first-page":"2012","article-title":"MuST-C: a multilingual speech translation corpus","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Di Gangi"},{"key":"ref39","article-title":"No language left behind: Scaling human-centered machine translation","author":"Costa-juss\u00e0","year":"2022"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889325.pdf?arnumber=10889325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:41Z","timestamp":1774416401000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889325","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}