{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:11:33Z","timestamp":1764400293990,"version":"3.46.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFF0907304"],"award-info":[{"award-number":["2024YFF0907304"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401560"],"award-info":[{"award-number":["62401560"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249087","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"1068-1073","source":"Crossref","is-referenced-by-count":0,"title":["HIPA-MoE: A Parameter-Efficient Fine-Tuning Architecture with Hierarchical Adapter-Based Mixture-Of-Experts for Multilingual ASR"],"prefix":"10.1109","author":[{"given":"Xun","family":"Lu","sequence":"first","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaofeng","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.570"},{"key":"ref2","article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","volume-title":"arXiv","author":"Zhang","year":"2023"},{"issue":"1","key":"ref3","first-page":"97:4798","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447399"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34805"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887679"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887955"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888133"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890533"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889526"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-4003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-480"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2292"},{"article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"presented at the International Conference on Learning Representations","author":"Hu","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445894"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887809"},{"key":"ref17","article-title":"Whistle: Data-efficient multilingual and crosslingual speech recognition via weakly phonetic supervision","volume-title":"arXiv","author":"Yusuyin","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447568"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1714"},{"key":"ref20","article-title":"ML-SUPERB 2.0: Benchmarking multilingual speech models across modeling constraints, languages, and datasets","author":"Shi","year":"2024","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/N19-4009","article-title":"Fairseq: A Fast, Extensible Toolkit for Sequence Modeling","volume-title":"arXiv","author":"Ott","year":"2019"},{"key":"ref22","article-title":"XLS-R: Selfsupervised cross-lingual speech representation learning at scale","volume-title":"arXiv","author":"Babu","year":"2021"},{"key":"ref23","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","volume":"abs\/2006.16668","author":"Lepikhin","year":"2020","journal-title":"ArXiv"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249087.pdf?arnumber=11249087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:08:38Z","timestamp":1764400118000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249087","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}