{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:20:23Z","timestamp":1774419623223,"version":"3.50.1"},"reference-count":41,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888357","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Speech Re-Painting for Robust ASR"],"prefix":"10.1109","author":[{"given":"Kyle","family":"Kastner","sequence":"first","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gary","family":"Wang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Isaac","family":"Elias","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takaaki","family":"Saeki","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro Moreno","family":"Mengibar","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7oise","family":"Beaufays","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref2","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389676"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094687"},{"key":"ref5","article-title":"Better speech synthesis through scaling","author":"Betker","year":"2023"},{"key":"ref6","article-title":"Improving image generation with better captions","author":"Betker","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053831"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746475"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448074"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095702"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref14","article-title":"Gemini: a family of highly capable multimodal models","author":"Tea","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178863"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746217"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1882"},{"key":"ref18","article-title":"Denoising lm: Pushing the limits of error correction models for speech recognition","author":"Gu","year":"2024"},{"key":"ref19","article-title":"Ask me anything: A simple strategy for prompting language models","author":"Arora","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447240"},{"key":"ref21","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref22","first-page":"2917","article-title":"Style equalization: Unsupervised learning of controllable generative sequence models","volume-title":"Proc. ICML","author":"Chang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448361"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096429"},{"key":"ref26","article-title":"Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities","author":"Kong","year":"2024"},{"key":"ref27","article-title":"AudioPaLM: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.799893"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-194"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1461"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref34","article-title":"Auto-encoding variational bayes","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref35","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096820"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248089"}],"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\/10888357.pdf?arnumber=10888357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:48Z","timestamp":1774416228000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888357\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888357","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}