{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:33:39Z","timestamp":1776890019597,"version":"3.51.2"},"reference-count":44,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","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\/icassp49660.2025.10889634","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":["Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding"],"prefix":"10.1109","author":[{"given":"Jiahui","family":"Zhao","sequence":"first","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Shi","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenrui","family":"Cui","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianrui","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hexin","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,College of Computing and Data Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaoheng","family":"Ni","sequence":"additional","affiliation":[{"name":"Meta,New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingxuan","family":"Ye","sequence":"additional","affiliation":[{"name":"Institute of Acoustics,Key Laboratory of Speech Acoustics and Content Understanding,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref2","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"issue":"97","key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3566210"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448335"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447667"},{"key":"ref8","author":"Zhang","year":"2023","journal-title":"Google USM: Scaling automatic speech recognition beyond 100 languages"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3407511"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889111"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2525"},{"key":"ref12","author":"Shi","journal-title":"On the effectiveness of asr representations in real-world noisy speech emotion recognition"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1577"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2350"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980071"},{"key":"ref16","author":"Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1446"},{"key":"ref18","author":"Song","year":"2022","journal-title":"Monolingual recognizers fusion for code-switching speech recognition"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11426"},{"key":"ref20","author":"Shi","year":"2024","journal-title":"Exploration of adapter for noise robust automatic speech recognition"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2385"},{"key":"ref22","author":"Kulkarni","year":"2023","journal-title":"Adapting the adapters for code-switching in multilingual asr"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2485"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-923"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389662"},{"key":"ref26","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":"ref27","author":"Tseng","year":"2021","journal-title":"Mandarin-english code-switching speech recognition with self-supervised speech representation models"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446258"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832330"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2032"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/apsipaasc63619.2025.10849308"},{"key":"ref32","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"Proc. ICML","author":"Houlsby"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-024-00349-3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094883"},{"key":"ref35","article-title":"Adapter Integration: Mitigating catastrophic forgetting in multi-language and multi-accent whisper asr model fine-tuning","author":"Huang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-892"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-015-9303-x"},{"key":"ref38","author":"Peng","year":"2022","journal-title":"Internal language model estimation based language model fusion for cross-domain code-switching speech recognition"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-262"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095878"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3307350"},{"key":"ref42","author":"Liu","year":"2024","journal-title":"Aligning speech to languages to enhance code-switching speech recognition"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446652"},{"key":"ref44","author":"Zhang","year":"2022","journal-title":"Intermediate-layer output regularization for attention-based speech recognition with shared decoder"}],"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\/10889634.pdf?arnumber=10889634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:48Z","timestamp":1774416408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889634\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889634","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}