{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:19:13Z","timestamp":1774419553488,"version":"3.50.1"},"reference-count":29,"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\/icassp49660.2025.10888151","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":0,"title":["BANC: Towards Efficient Binaural Audio Neural Codec for Overlapping Speech"],"prefix":"10.1109","author":[{"given":"Anton","family":"Ratnarajah","sequence":"first","affiliation":[{"name":"University of Maryland,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shi-Xiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2939"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682435"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053220"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref5","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"CoRR"},{"key":"ref6","article-title":"Hifi-codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref8","article-title":"The dominant role of low-frequency interaural time differences in sound localization","volume-title":"The Journal of the Acoustical Society of America","volume":"91","author":"Wightman","year":"1992"},{"key":"ref9","article-title":"Definition of the opus audio codec","volume-title":"RFC","volume":"6716","author":"Valin"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.1912679"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.540325"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168385"},{"key":"ref13","article-title":"Overview of the evs codec architecture","volume-title":"ICASSP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00805"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747846"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548253"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094770"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632680"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref20","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kong","year":"2020"},{"key":"ref21","article-title":"Neural discrete representation learning","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"van den Oord","year":"2017"},{"key":"ref22","article-title":"Noisy speech database for training speech enhancement algorithms and TTS models","author":"Valentini-Botinhao","year":"2017"},{"key":"ref23","article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052932"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-230"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688304"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053215"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"}],"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\/10888151.pdf?arnumber=10888151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:28Z","timestamp":1774416208000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888151","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}