{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T18:45:28Z","timestamp":1786733128391,"version":"build-2736575974"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government","award":["24ZC1100"],"award-info":[{"award-number":["24ZC1100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/jstsp.2024.3491576","type":"journal-article","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T18:40:18Z","timestamp":1730918418000},"page":"1490-1505","source":"Crossref","is-referenced-by-count":2,"title":["Perceptual Neural Audio Coding With Modified Discrete Cosine Transform"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5620-8367","authenticated-orcid":false,"given":"Hyungseob","family":"Lim","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0654-2639","authenticated-orcid":false,"given":"Jihyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0786-3902","authenticated-orcid":false,"given":"Byeong Hyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2237-2668","authenticated-orcid":false,"given":"Inseon","family":"Jang","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6554-0783","authenticated-orcid":false,"given":"Hong-Goo","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-0327-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.197157"},{"key":"ref4","volume-title":"PsychoacousticsFacts and Models","author":"Fastl","year":"1990"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169405"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3403\/00629116u"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3403\/01007714"},{"issue":"10","key":"ref8","first-page":"789","article-title":"ISO\/IEC MPEG-2 advanced audio coding","volume":"45","author":"Bosi","year":"1997","journal-title":"J. Audio Eng. Soc."},{"key":"ref9","first-page":"54","article-title":"AC-2 and AC-3: Low-complexity transform-based audio coding","volume-title":"Proc. Audio Eng. Soc. Conf.: Collected Papers Digit. Audio Bit-Rate Reduction","author":"Fielder","year":"1996"},{"key":"ref10","article-title":"Information technologyMPEG audio technologies  Part 3: Unified speech and audio coding, ISO\/IEC 23003-3","year":"2020"},{"key":"ref11","first-page":"1","article-title":"High-quality, low-delay music coding in the opus codec","volume":"135","author":"Valin","year":"2013","journal-title":"Audio Eng. Soc. Conv."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3034501"},{"key":"ref14","first-page":"1","article-title":"End-to-end optimized image compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ball","year":"2017"},{"key":"ref15","first-page":"1","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ball","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"ref17","first-page":"11913","article-title":"High-fidelity generative image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mentzer","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129353"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747527"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref23","first-page":"1","article-title":"High fidelity neural audio compression","volume":"2023","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref24","first-page":"27980","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2305"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097001"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446359"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096243"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414913"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","article-title":"Method for the subjective assessment of intermediate quality level of audio systems","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937179"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3069302"},{"key":"ref35","article-title":"Method of objective measurements of perceived audio quality","year":"2001"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.116122"},{"key":"ref37","first-page":"17","article-title":"Temporal noise shaping, qualtization and coding methods in perceptual audio coding: A tutorial introduction","volume-title":"Proc. Audio Eng. Soc. Conf.: High- Qual. Audio Coding","author":"Herre","year":"1999"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804299"},{"key":"ref39","first-page":"49","article-title":"Spectral band replication, a novel approach in audio coding","volume":"112","author":"Dietz","year":"2002","journal-title":"Audio Eng. Soc. Conv."},{"issue":"142\/163","key":"ref40","article-title":"Coding theorems for a discrete source with a fidelity criterion","volume":"4","author":"Shannon","year":"1959","journal-title":"IRE Nat. Conv. Rec"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref42","first-page":"1141","article-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Agustsson","year":"2017"},{"key":"ref43","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oord","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00324"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01039"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.930649"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref49","article-title":"Method for the subjective assessment of small impairments in audio systems","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1191"},{"key":"ref51","first-page":"1","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00652"},{"key":"ref53","first-page":"675","article-title":"Rethinking lossy compression: The rate-distortion-perception tradeoff","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blau","year":"2019"},{"key":"ref54","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150852"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/214762.214771"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1952.273898"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3039765"},{"key":"ref60","article-title":"Subjective evaluation of blind audio source separation database: SEBASS-DB","author":"Kastner"},{"key":"ref61","article-title":"MUSDB18-HQ - an uncompressed version of MUSDB18","author":"Rafii","year":"2019"},{"key":"ref62","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit, [sound]","author":"Veaux","year":"2017"},{"key":"ref63","article-title":"Workplan on speech and audio material selection","volume-title":"Proc. 84th MPEG meeting of ISO\/IEC JTC 1\/SC 29\/WG 11","year":"2008"},{"key":"ref64","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref65","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref66","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref67","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/10874827\/10746393.pdf?arnumber=10746393","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:37:43Z","timestamp":1738867063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10746393\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":68,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3491576","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}