{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:36:58Z","timestamp":1780587418788,"version":"3.54.1"},"reference-count":81,"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":[{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"name":"Korea Government","award":["2021-0-00456"],"award-info":[{"award-number":["2021-0-00456"]}]},{"name":"Development of Ultra-high Speech Quality Technology for Remote Multi-speaker Conference System"}],"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.2024.3469530","type":"journal-article","created":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T18:36:00Z","timestamp":1727462160000},"page":"1517-1530","source":"Crossref","is-referenced-by-count":15,"title":["HILCodec: High-Fidelity and Lightweight Neural Audio Codec"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6799-6821","authenticated-orcid":false,"given":"Sunghwan","family":"Ahn","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beom Jun","family":"Woo","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8086-5009","authenticated-orcid":false,"given":"Min Hyun","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9047-5353","authenticated-orcid":false,"given":"Chanyeong","family":"Moon","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0568-4902","authenticated-orcid":false,"given":"Nam Soo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering and Institute of New Media and Communications, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1975.9792"},{"key":"ref3","first-page":"360","article-title":"Adaptive predictive coding of speech signals","volume-title":"Proc. Conf. Commun. Process.","author":"Atal","year":"1967"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/79.952802"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1984.1162229"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MP.2006.1664069"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/78.258122"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415603"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178954"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959505"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/5.842996"},{"issue":"10","key":"ref13","first-page":"780","article-title":"ISO\/MPEG-1 audio: A genereic standard for coding of high quality digital audio","volume":"40","author":"Brandenburg","year":"1994","journal-title":"J. Audio Eng. Soc."},{"issue":"10","key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599639"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1563"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413439"},{"key":"ref18","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref19","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner","year":"2018"},{"key":"ref20","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oord","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref22","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref24","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Int. conf. Adv. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref25","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2019"},{"key":"ref26","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26479"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref29","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053113"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747733"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746670"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3132557"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.1990.117117"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref39","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref41","article-title":"HiFi-Codec: Group-residual vector quantization for high fidelity audio codec","author":"Yang","year":"2023"},{"key":"ref42","first-page":"27980","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref44","first-page":"5591","article-title":"Gradient descent GAN optimization is locally stable","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Nagarajan","year":"2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref46","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/3-540-49430-8_2","article-title":"Efficient backprop","volume-title":"Neural Networks: Tricks of the Trade","author":"LeCun","year":"1998"},{"key":"ref50","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clevert","year":"2016"},{"key":"ref51","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref52","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Salimans","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref54","article-title":"Mixed precision training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Micikevicius","year":"2018"},{"key":"ref55","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Oord","year":"2017"},{"key":"ref56","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2023"},{"key":"ref57","article-title":"AdamP: Slowing down the slowdown for momentum optimizers on scale-invariant weights","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Heo","year":"2021"},{"key":"ref58","article-title":"SGDR: Stochastic gradient descent with restarts","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"ref60","first-page":"11913","article-title":"High-fidelity generative image compression","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Mentzer","year":"2020"},{"key":"ref61","first-page":"19964","article-title":"Batch normalization biases residual blocks towards the identity function in deep networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"De","year":"2020"},{"key":"ref62","article-title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"ref64","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref65","article-title":"The MTG-Jamendo dataset for automatic music tagging","volume-title":"Proc. Mach. Learn. Music Discov. Workshop, Int. Conf. Mach. Learn.","author":"Bogdanov","year":"2019"},{"key":"ref66","volume-title":"Method for the Subjective Assessment of Intermediate Quality Level of Coding Systems","year":"2015"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.5334\/jors.187"},{"key":"ref69","article-title":"ONNX runtime","year":"2021"},{"key":"ref70","article-title":"Fixup initialization: Residual learning without normalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2019"},{"key":"ref71","first-page":"1352","article-title":"ReZero is all you need: Fast convergence at large depth","volume-title":"Proc. 37th Conf. Uncertainty Artif. Intell.","author":"Bachlechner","year":"2021"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1002\/0470041978"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447523"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1490"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447532"},{"key":"ref77","article-title":"ASPEC: Adaptive spectral entropy coding of high quality music signals","volume-title":"Proc. 90th Conv. Audio Eng. Soc.","author":"Brandenburg","year":"1991"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3403\/01007714"},{"key":"ref79","article-title":"Recommendati on BS.1387-2: Method for objective measurement of perceived audio quality"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937179"},{"key":"ref81","article-title":"An examination and interpretation of ITU-R BS.1387: Perceptual evaluation of audio quality","author":"Kabal","year":"2002"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/10874827\/10697269.pdf?arnumber=10697269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:38:14Z","timestamp":1738867094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10697269\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":81,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3469530","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}