{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:21:26Z","timestamp":1774419686731,"version":"3.50.1"},"reference-count":32,"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"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889560","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Attention Weighting and Conditional Entropy-driven Quantization Loss for Neural Audio Codecs"],"prefix":"10.1109","author":[{"given":"Huiyu","family":"Zhang","sequence":"first","affiliation":[{"name":"Wuhan University,NERCMS, School of Computer Science, Hubei Luojia Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiping","family":"Tu","sequence":"additional","affiliation":[{"name":"Wuhan University,NERCMS, School of Computer Science, Hubei Luojia Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Wuhan University,NERCMS, School of Computer Science, Hubei Luojia Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinmeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Wuhan University,NERCMS, School of Computer Science, Hubei Luojia Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanzhen","family":"Ren","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Cyber Science and Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Wuhan University,NERCMS, School of Computer Science, Hubei Luojia Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1976.1170021"},{"issue":"10","key":"ref2","first-page":"780","article-title":"ISO\/MPEG-1 audio: A generic standard for coding of high-quality digital audio","volume":"42","author":"Brandenburg","year":"1994","journal-title":"AES"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/25.312763"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164946"},{"key":"ref5","volume-title":"Techniques and standards for image, video, and audio coding.","author":"Rao","year":"1996"},{"key":"ref6","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref9","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447744"},{"key":"ref12","article-title":"High-fidelity audio compression with improved rvqgan","author":"Kumar","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447523"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095442"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445966"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-37454-8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00571"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129353"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3039765"},{"key":"ref20","article-title":"Codec-superb @ slt 2024: Codec speech processing universal performance benchmark","volume-title":"Online Report","year":"2024"},{"key":"ref21","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.616"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179090"},{"key":"ref26","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref27","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref28","article-title":"Noisy speech database for training speech enhancement algorithms and TTS models","author":"Valentini-Botinhao","year":"2017","journal-title":"University of Edinburgh. CSTR"},{"key":"ref29","article-title":"Gunshots recorded in an open field using ipod touch devices","author":"Cooper","year":"2020","journal-title":"Dryad, Dataset"},{"key":"ref30","article-title":"Itu-r recommendation bs 1534-3, \u201dmethod for the subjective assessment of intermediate quality levels of coding systems (MUSHRA)","volume-title":"Tech. Rep.","year":"2015"},{"key":"ref31","article-title":"Definition of the opus audio codec","volume-title":"Tech. Rep.","author":"Valin","year":"2012"},{"key":"ref32","volume-title":"The speex codec manual version 1.2 beta 3","author":"Valin","year":"2007"}],"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\/10889560.pdf?arnumber=10889560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:07Z","timestamp":1774416247000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889560\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889560","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}