{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:10:48Z","timestamp":1775326248833,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1109\/apsipaasc63619.2025.10849308","type":"proceedings-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T18:37:05Z","timestamp":1738003025000},"page":"1-6","source":"Crossref","is-referenced-by-count":10,"title":["Adapting OpenAI\u2019s Whisper for Speech Recognition on Code-Switch Mandarin-English SEAME and ASRU2019 Datasets"],"prefix":"10.1109","author":[{"given":"Yuhang","family":"Yang","sequence":"first","affiliation":[{"name":"Hunan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yizhou","family":"Peng","sequence":"additional","affiliation":[{"name":"National University of Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Huang","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Computer Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xionghu","family":"Zhong","sequence":"additional","affiliation":[{"name":"Hunan University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389662"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746830"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747537"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-021-00222-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-3214"},{"key":"ref6","article-title":"Code-switch language model with inversion constraints for mixed language speech recognition","volume-title":"Proceedings of COLING 2012","author":"Li"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2219"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854536"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746554"},{"key":"ref11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1493"},{"key":"ref13","article-title":"Bertologicomix: How does code-mixing interact with multilingual bert?","volume-title":"Proceedings of Adapt-NLP","author":"Santy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.80"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-606"},{"key":"ref17","article-title":"Internal language model estimation based language model fusion for cross-domain code-switching speech recognition","author":"Peng","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414158"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2485"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11426"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682850"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095878"},{"key":"ref23","article-title":"Mandarin-english code-switching speech recognition with self-supervised speech representation models","author":"Tseng","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref25","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref26","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref27","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2589"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1044"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1440"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1537"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1916"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1505"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2032"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-015-9303-x"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1093\/oed\/4103914415"},{"key":"ref38","article-title":"The asru 2019 mandarin-english code-switching speech recognition challenge: Open datasets, tracks, methods and results","author":"Shi","year":"2020"},{"key":"ref39","article-title":"Mixed precision training","author":"Micikevicius","year":"2017"},{"key":"ref40","volume-title":"ESPnet2-SEAME-recipe"},{"key":"ref41","article-title":"U2++: Unified two-pass bidirectional end-to-end model for speech recognition","author":"Wu","year":"2021"}],"event":{"name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Macau, Macao","start":{"date-parts":[[2024,12,3]]},"end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10848542\/10848533\/10849308.pdf?arnumber=10849308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T06:08:30Z","timestamp":1738044510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10849308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc63619.2025.10849308","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}