{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:02:26Z","timestamp":1776888146062,"version":"3.51.2"},"reference-count":30,"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\/icassp49660.2025.10890482","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses"],"prefix":"10.1109","author":[{"given":"Yufeng","family":"Yang","sequence":"first","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Desh","family":"Raj","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ju","family":"Lin","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Niko","family":"Moritz","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junteng","family":"Jia","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gil","family":"Keren","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Egor","family":"Lakomkin","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiteng","family":"Huang","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacob","family":"Donley","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jay","family":"Mahadeokar","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ozlem","family":"Kalinli","sequence":"additional","affiliation":[{"name":"Meta,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Project Aria: A new tool for egocentric multi-modal AI research","author":"Engel","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref4","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"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.2021-1775"},{"key":"ref8","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref9","article-title":"Spatial HuBERT: Self-supervised spatial speech representation learning for a single talker from multi-channel audio","author":"Dimitriadis","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29951"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448072"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2076"},{"key":"ref13","first-page":"3915","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"Proc. International Conference on Machine Learning","author":"Chiu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10626364"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2024-2"},{"key":"ref18","article-title":"EasyCom: An augmented reality dataset to support algorithms for easy communication in noisy environments","author":"Donley","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414123"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447278"},{"key":"ref21","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. International Conference on Learning Representations","author":"Simonyan"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0999"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446861"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01029"},{"key":"ref28","article-title":"Audio visual speaker localization from egocentric views","author":"Zhao","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72691-0_15"}],"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\/10890482.pdf?arnumber=10890482","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:58Z","timestamp":1774416358000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890482\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890482","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}