{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:32:06Z","timestamp":1776882726278,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210181","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["STFTCodec: High-Fidelity Audio Compression through Time-Frequency Domain Representation"],"prefix":"10.1109","author":[{"given":"Tao","family":"Feng","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Xie","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqi","family":"Ye","sequence":"additional","affiliation":[{"name":"Peking University,Shenzhen Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyang","family":"Luo","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Guan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832364"},{"key":"ref2","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref3","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref4","article-title":"Definition of the opus audio codec","author":"Valin","year":"2012","journal-title":"Tech. Rep."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref6","article-title":"Neural discrete representation learning","volume":"30","author":"van den Oord","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"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","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref12","article-title":"Vocos: Closing the gap between time-domain and fourier-based neural vocoders for high-quality audio synthesis","author":"Siuzdak","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3417347"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832214"},{"key":"ref15","first-page":"4352","article-title":"Adversarial generation of time-frequency features with application in audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Marafioti"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096056"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096243"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref19","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref22","article-title":"Bigcodec: Pushing the limits of low-bitrate neural speech codec","author":"Xin","year":"2024"},{"key":"ref23","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"Kumar","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref24","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Veaux","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref30","article-title":"Method for the subjective assessment of intermediate quality level of audio systems","volume":"2","author":"Series","year":"2014","journal-title":"Int. Telecommun. Union Radiocommun. Assembly"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210181.pdf?arnumber=11210181","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:09:12Z","timestamp":1761930552000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210181\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210181","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}