{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:16:04Z","timestamp":1764400564520,"version":"3.46.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249345","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"676-681","source":"Crossref","is-referenced-by-count":0,"title":["A High-Quality and Low-Complexity Streamable Neural Speech Codec with Knowledge Distillation"],"prefix":"10.1109","author":[{"given":"En-Wei","family":"Zhang","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui-Peng","family":"Du","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Hang","family":"Jiang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Ai","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/25.312763"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP63861.2024.10800013"},{"key":"ref3","article-title":"SpeechTokenizer: Unified speech tokenizer for speech large language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447774"},{"key":"ref7","article-title":"High-quality, low-delay music coding in the opus codec","volume-title":"Audio Engineering Society Convention 135","author":"Valin","year":"2013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref10","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref11","article-title":"High-fidelity audio compression with improved rvqgan","volume-title":"Proc. NeurIPS","volume":"36","author":"Kumar","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3417347"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2025.3560172"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref15","first-page":"16 133","article-title":"ConvNeXt v2: Codesigning and scaling convnets with masked autoencoders","volume-title":"Proc. CVPR","author":"Woo","year":"2023"},{"key":"ref16","article-title":"Finite scalar quantization: VQ-VAE made simple","volume-title":"Proc. ICLR","author":"Mentzer","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-50"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3579310"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832214"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2010.5495701"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"volume-title":"The livermore fortran kernels: A computer test of the numerical performance range","year":"1986","author":"McMahon","key":"ref24"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249345.pdf?arnumber=11249345","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:11:37Z","timestamp":1764400297000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249345\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249345","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}