{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:11:39Z","timestamp":1775200299696,"version":"3.50.1"},"reference-count":37,"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\/asru65441.2025.11434784","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":0,"title":["Deep Audio Zooming: Creating a Sound Barrier With Microphone Array Processing"],"prefix":"10.1109","author":[{"given":"Meng","family":"Yu","sequence":"first","affiliation":[{"name":"Tencent AI Lab,Bellevue,WA,USA"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,WA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"key":"ref2","article-title":"Microphone array signal processing","volume":"1","author":"Benesty","year":"2008","journal-title":"Springer Science Business Media"},{"key":"ref3","article-title":"Acoustical zooming based on a parametric sound field representation","author":"Schultz-Amling","year":"2010","journal-title":"128th AES Convention"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6953348"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-53547-0_12"},{"key":"ref6","article-title":"Audio zoom for smartphones based on multiple adaptive beamformers","volume-title":"ACM International Conference on Multimedia","author":"Nair"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639593"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682470"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2881912"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2266"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3181"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1521"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-625"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747141"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3202129"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8903121"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616138"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054538"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268969"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8461930"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472644"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2124"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393713"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688198"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-430"},{"key":"ref30","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv:1607.06450"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref32","article-title":"NeuralEcho: A self-attentive recurrent neural network for unified acoustic echo suppression and speech enhancement","author":"Yu","year":"2022","journal-title":"arXiv preprint arXiv:2205.10401"},{"key":"ref33","article-title":"AISHELL-2: Transforming mandarin asr research into industrial scale","author":"Du","year":"2018","journal-title":"arXiv:1808.10583"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09905-3"},{"key":"ref35","article-title":"Recommendation p.862: Perceptual evaluation of speech quality (pesq), an objective method for endtoend speech quality assessment of narrowband telephone networks and speech codecs","year":"2001"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746108"}],"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\/11434784.pdf?arnumber=11434784","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:46Z","timestamp":1775192386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434784\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434784","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}