{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:17:06Z","timestamp":1776885426841,"version":"3.51.2"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434647","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["MMW: Side Talk Rejection Multi-Microphone Whisper On Smart Glasses"],"prefix":"10.1109","author":[{"given":"Yang","family":"Liu","sequence":"first","affiliation":[{"name":"Meta,US"}]},{"given":"Li","family":"Wan","sequence":"additional","affiliation":[{"name":"Meta,US"}]},{"given":"Yiteng","family":"Huang","sequence":"additional","affiliation":[{"name":"Meta,US"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Meta,US"}]},{"given":"Yangyang","family":"Shi","sequence":"additional","affiliation":[{"name":"Meta,US"}]},{"given":"Saurabh","family":"Adya","sequence":"additional","affiliation":[{"name":"Meta,US"}]},{"given":"Ming","family":"Sun","sequence":"additional","affiliation":[{"name":"Meta,US"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[{"name":"Meta,US"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/29.32276"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966291"},{"key":"ref9","first-page":"105","article-title":"Many-to-many audio spectrogram tansformer: Transformer for sound event localization and detection","author":"Park","year":"2021","journal-title":"DCASE"},{"key":"ref10","article-title":"Bat: Learning to reason about spatial sounds with large language models","author":"Zheng","year":"2024","journal-title":"arXiv preprint arXiv:2402.01591"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2419"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0647"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746624"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01950-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1056"},{"key":"ref16","article-title":"Salmonn: Towards generic hearing abilities for large language models","author":"Tang","year":"2023","journal-title":"arXiv preprint arXiv:2310.13289"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.361"},{"issue":"2","key":"ref18","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref19","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning. PMLR","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447492"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-971"},{"key":"ref22","article-title":"Dicow: Diarization-conditioned whisper for target speaker automatic speech recognition","author":"Polok","year":"2024","journal-title":"arXiv preprint arXiv:2501.00114"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887683"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2025-82"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-024-00349-3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-322"},{"key":"ref27","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv preprint arXiv:2111.00396"},{"key":"ref28","first-page":"1474","article-title":"Hippo: Recurrent memory with optimal polynomial projections","volume":"33","author":"Gu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","article-title":"Long range arena: A benchmark for efficient transformers","author":"Tay","year":"2020","journal-title":"arXiv preprint arXiv:2011.04006"},{"key":"ref31","article-title":"Transformers are ssms: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024","journal-title":"arXiv preprint arXiv:2405.21060"},{"key":"ref32","first-page":"4733","article-title":"Learning representations from audio-visual spatial alignment","volume":"33","author":"Morgado","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00995"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00204"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3189"},{"key":"ref36","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv:1711.05101"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1280"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3318398"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1788"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434647.pdf?arnumber=11434647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:42Z","timestamp":1775192262000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434647\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434647","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}