{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:15Z","timestamp":1775230095839,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832240","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"431-438","source":"Crossref","is-referenced-by-count":6,"title":["Crossmodal ASR Error Correction With Discrete Speech Units"],"prefix":"10.1109","author":[{"given":"Yuanchao","family":"Li","sequence":"first","affiliation":[{"name":"University of Edinburgh,UK"}]},{"given":"Pinzhen","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Edinburgh,UK"}]},{"given":"Peter","family":"Bell","sequence":"additional","affiliation":[{"name":"University of Edinburgh,UK"}]},{"given":"Catherine","family":"Lai","sequence":"additional","affiliation":[{"name":"University of Edinburgh,UK"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023428"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2362"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2078"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094910"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-555"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746289"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1430"},{"key":"ref12","article-title":"Generative speech recognition error correction with large language models","author":"Huck Yang","year":"2023","journal-title":"arXiv preprint arXiv:2309.15649"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053126"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3557894"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094690"},{"key":"ref16","article-title":"Cross-modal ASR post-processing system for error correction and utterance rejection","author":"Du","year":"2022","journal-title":"arXiv preprint arXiv:2201.03313"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.618"},{"key":"ref18","article-title":"It\u2019s never too late: Fusing acoustic information into large language models for automatic speech recognition","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2402.05457"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1242"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1992"},{"key":"ref21","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference (LREC)","author":"Ardila"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683745"},{"key":"ref28","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016","journal-title":"arXiv preprint arXiv:1609.08144"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.114"},{"key":"ref31","first-page":"261","article-title":"WIT3: Web inventory of transcribed and translated talks","volume-title":"Proceedings of the 16th Annual Conference of the European Association for Machine Translation","author":"Cettolo"},{"key":"ref32","article-title":"Word-level acoustic modeling with convolutional vector regression","volume-title":"Proc. ICML Workshop Representation Learn","author":"Maas"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707765"},{"key":"ref34","article-title":"Analyzing autoencoder-based acoustic word embeddings","volume-title":"ICLR Workshop on Bridging AI and Cognitive Science","author":"Matusevych"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096099"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10627629"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref38","article-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832240.pdf?arnumber=10832240","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:17:53Z","timestamp":1737101873000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832240\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832240","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}