{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T22:51:37Z","timestamp":1769640697655,"version":"3.49.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T00:00:00Z","timestamp":1725840000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T00:00:00Z","timestamp":1725840000000},"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":[[2024,9,9]]},"DOI":"10.1109\/iwaenc61483.2024.10694300","type":"proceedings-article","created":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T17:31:16Z","timestamp":1728063076000},"page":"344-348","source":"Crossref","is-referenced-by-count":2,"title":["High-Fidelity Diffusion-Based Audio Codec"],"prefix":"10.1109","author":[{"given":"Zhengpu","family":"Zhang","sequence":"first","affiliation":[{"name":"ByteDance,Streaming Audio IA,China"}]},{"given":"Jianyuan","family":"Feng","sequence":"additional","affiliation":[{"name":"ByteDance,Data Speech,China"}]},{"given":"Yongjian","family":"Mao","sequence":"additional","affiliation":[{"name":"ByteDance,Data Speech,China"}]},{"given":"Yehang","family":"Zhu","sequence":"additional","affiliation":[{"name":"ByteDance,Streaming Audio IA,China"}]},{"given":"Junjie","family":"Shi","sequence":"additional","affiliation":[{"name":"ByteDance,Streaming Audio IA,China"}]},{"given":"Xuzhou","family":"Ye","sequence":"additional","affiliation":[{"name":"ByteDance,Streaming Audio IA,China"}]},{"given":"Shilei","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance,Streaming Audio IA,China"}]},{"given":"Derong","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance,Streaming Audio IA,China"}]},{"given":"Chuanzeng","family":"Huang","sequence":"additional","affiliation":[{"name":"ByteDance,Streaming Audio IA,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-430"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref3","article-title":"High fidelity neural audio compression","author":"De \u0301fossez","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415120"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248100"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref10","article-title":"Hifi-codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023"},{"key":"ref11","article-title":"Variational image compression with a scale hyperprior","author":"Ball\u00e9","year":"2018"},{"key":"ref12","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref13","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Universal speech enhancement with score-based diffusion","author":"Serr\u00e0","year":"2022"},{"key":"ref16","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref17","article-title":"Adversarial score matching and improved sampling for image generation","author":"Jolicoeur-Martineau","year":"2020"},{"key":"ref18","article-title":"On tuning consistent annealed sampling for denoising score matching","author":"Serr\u00e0","year":"2021"},{"key":"ref19","first-page":"579","article-title":"CRASH: raw audio score-based generative modeling for controllable high-resolution drum sound synthesis","volume-title":"Proc. of the Int. Soc. for Music Information Retrieval Conf. (ISMIR)","author":"Rouard"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref21","article-title":"Mixture density networks","volume-title":"Technical report","author":"Bishop","year":"1994"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.860325"},{"key":"ref24","article-title":"Density modeling of images using a generalized normalization transformation","author":"Ball\u00e9","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095442"},{"key":"ref26","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445966"},{"key":"ref28","article-title":"ICASSP 2022 Deep Noise Suppression Challenge","author":"Harishchandra","year":"2022","journal-title":"ICASSP"},{"key":"ref29","article-title":"Musdb18-a corpus for music separation","author":"Rafii","year":"2017","journal-title":"HAL, Tech. Rep."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref31","article-title":"ITU-R Recommendation BS 1534-3. Method for the subjective assessment of intermediate quality levels of coding systems","year":"2015"},{"key":"ref32","article-title":"Noisy speech database for training speech enhancement algorithms and TTS models","author":"Valentini-Botinhao","year":"2017"},{"key":"ref33","article-title":"Sound quality assessment material recordings for subjective tests: Users\u2019 handbook for the EBU SQAM CD","volume-title":"European Broadcasting Union, Tech. Rep. EBU\u2013TECH 3253","author":"Union","year":"2008"}],"event":{"name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","location":"Aalborg, Denmark","start":{"date-parts":[[2024,9,9]]},"end":{"date-parts":[[2024,9,12]]}},"container-title":["2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10693863\/10693957\/10694300.pdf?arnumber=10694300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T17:41:39Z","timestamp":1728322899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10694300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,9]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/iwaenc61483.2024.10694300","relation":{},"subject":[],"published":{"date-parts":[[2024,9,9]]}}}