{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:38:32Z","timestamp":1753601912343,"version":"3.28.0"},"reference-count":18,"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\/icassp48485.2024.10446800","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10586-10590","source":"Crossref","is-referenced-by-count":2,"title":["Extending Multilingual ASR to New Languages Using Supplementary Encoder and Decoder Components"],"prefix":"10.1109","author":[{"given":"Yerbolat","family":"Khassanov","sequence":"first","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianfeng","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tze Yuang","family":"Chong","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Lu","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zejun","family":"Ma","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning (ICML)","volume":"202","author":"Radford"},{"article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","year":"2023","author":"Zhang","key":"ref2"},{"article-title":"Scaling speech technology to 1,000+ languages","year":"2023","author":"Pratap","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746223"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023274"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1061"},{"key":"ref8","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"International Conference on Machine Learning (ICML)","volume":"97","author":"Houlsby"},{"article-title":"Towards a unified view of parameter-efficient transfer learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"He","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746594"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10023141"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1166"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","year":"2022","author":"Bapna","key":"ref18"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446800.pdf?arnumber=10446800","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:26:12Z","timestamp":1722576372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446800\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446800","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}