{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:10:12Z","timestamp":1776885012609,"version":"3.51.2"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[],"published-print":{"date-parts":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389732","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":16,"title":["Prompting Large Language Models for Zero-Shot Domain Adaptation in Speech Recognition"],"prefix":"10.1109","author":[{"given":"Yuang","family":"Li","sequence":"first","affiliation":[{"name":"University of Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","article-title":"Sequence transduction with recurrent neural networks","volume-title":"in Proc. ICML","author":"Graves"},{"key":"ref3","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"in Proc. NeurIPS","author":"Chorowski"},{"key":"ref4","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv preprint arXiv:2212.04356"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688232"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref8","article-title":"On using monolingual corpora in neural machine translation","author":"Gulcehre","year":"2015","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746908"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096895"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383515"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415039"},{"key":"ref14","article-title":"Internal language model adaptation with text-only data for end-to-end speech recognition","author":"Meng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10557"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095860"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-824"},{"issue":"8","key":"ref18","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1285"},{"key":"ref20","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint","author":"OpenAI","year":"2023"},{"key":"ref21","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","first-page":"125","article-title":"Ted-lium: an automatic speech recognition dedicated corpus","author":"Rousseau","year":"2012","journal-title":"in LREC"},{"key":"ref25","article-title":"Spgispeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition","author":"Patrick","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref27","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume-title":"Proc. NeurIPS","volume":"35","author":"Alayrac"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1849"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.ecnlp-1.3"},{"key":"ref33","article-title":"Minigpt-4: Enhancing visionlanguage understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref37","article-title":"Decoupled weight decay regularization","volume-title":"in Proc. ICLR","author":"Loshchilov"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389732.pdf?arnumber=10389732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T17:45:25Z","timestamp":1743702325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389732","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}