{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:53:13Z","timestamp":1776181993002,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icasspw62465.2024.10626762","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"540-544","source":"Crossref","is-referenced-by-count":8,"title":["Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR And Speech-to-Text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision"],"prefix":"10.1109","author":[{"given":"Chih-Kai","family":"Yang","sequence":"first","affiliation":[{"name":"National Taiwan University"}]},{"given":"Kuan-Po","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Ke-Han","family":"Lu","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Chun-Yi","family":"Kuan","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Chi-Yuan","family":"Hsiao","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]}],"member":"263","reference":[{"key":"ref1","first-page":"7171","article-title":"Improving code-switched ASR with linguistic information","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics","author":"Chi"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095878"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.113"},{"key":"ref4","first-page":"12449","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Baevski"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-industry.29"},{"key":"ref10","article-title":"Seamlessm4t: Massively multilingual & multimodal machine translation","year":"2023"},{"key":"ref11","article-title":"Seamless: Multilingual expressive and streaming speech translation","year":"2023"},{"key":"ref12","article-title":"Scaling speech technology to 1,000+languages","author":"Pratap","year":"2023"},{"key":"ref13","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Radford"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389617"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446502"},{"key":"ref16","article-title":"Adapting the adapters for code-switching in multilingual asr","author":"Kulkarni","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref18","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Chiu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2032"},{"key":"ref20","article-title":"Ascend: A spontaneous chinese-english dataset for code-switching in multi-turn conversation","volume-title":"Proceedings of the 13th Language Resources and Evaluation Conference (LREC)","author":"Lovenia"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446737"},{"key":"ref22","article-title":"An exploration of in-context learning for speech language model","author":"Hsu","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448257"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10626762.pdf?arnumber=10626762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:53:34Z","timestamp":1723787614000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10626762\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10626762","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}