{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:45:22Z","timestamp":1776883522911,"version":"3.51.2"},"reference-count":34,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887679","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["M-MoE: Mixture of Mixture-of-Expert Model for CTC-based Streaming Multilingual ASR"],"prefix":"10.1109","author":[{"given":"Songjun","family":"Cao","sequence":"first","affiliation":[{"name":"Tencent Youtu Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yike","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Ma","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268945"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462201"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747905"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref10","article-title":"Multilingual end-to-end speech recognition with a single transformer on low-resource languages","author":"Zhou","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2847"},{"key":"ref12","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref13","article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref14","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023"},{"issue":"1","key":"ref15","first-page":"5232","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"The Journal of Machine Learning Research"},{"key":"ref16","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2020"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-478"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747065"},{"key":"ref19","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01591"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-480"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2292"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389760"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023346"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref28","article-title":"U2++: Unified two-pass bidirectional end-to-end model for speech recognition","author":"Wu","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref30","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-483"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1194"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389676"}],"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\/10887679.pdf?arnumber=10887679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:11Z","timestamp":1774416371000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887679","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}