{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T10:58:54Z","timestamp":1785841134879,"version":"3.56.0"},"reference-count":66,"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"}],"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.2024.3491575","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T18:36:20Z","timestamp":1730745380000},"page":"1462-1476","source":"Crossref","is-referenced-by-count":7,"title":["Neural Speech Coding for Real-Time Communications Using Constant Bitrate Scalar Quantization"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6051-6346","authenticated-orcid":false,"given":"Andreas","family":"Brendel","sequence":"first","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS in Erlangen, Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0987-863X","authenticated-orcid":false,"given":"Nicola","family":"Pia","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS in Erlangen, Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2203-4314","authenticated-orcid":false,"given":"Kishan","family":"Gupta","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS in Erlangen, Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2519-3579","authenticated-orcid":false,"given":"Lyonel","family":"Behringer","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS in Erlangen, Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1045-6064","authenticated-orcid":false,"given":"Guillaume","family":"Fuchs","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS in Erlangen, Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9545-1946","authenticated-orcid":false,"given":"Markus","family":"Multrus","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS in Erlangen, Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-023-00274-x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2887337"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053283"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053113"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747733"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448332"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682435"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053220"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632750"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3129994"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414605"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-430"},{"key":"ref18","first-page":"2835","article-title":"High fidelity neural audio compression","volume-title":"Proc. Trans. Mach. Learn. Res.","author":"Dfossez","year":"2023"},{"key":"ref19","first-page":"27980","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","volume":"36","author":"Kumar","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447523"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3461615.3491114"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746296"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3417347"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446556"},{"key":"ref26","first-page":"1526","article-title":"From discrete tokens to high-fidelity audio using multi-band diffusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Roman","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1563"},{"key":"ref28","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413680"},{"key":"ref30","first-page":"1141","article-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Agustsson","year":"2017"},{"key":"ref31","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst.","author":"Oord","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632723"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10084"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-537"},{"key":"ref35","article-title":"End-to-end optimized image compression","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ball","year":"2017"},{"key":"ref36","first-page":"12367","article-title":"Universally quantized neural compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Agustsson","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3034501"},{"key":"ref38","first-page":"2024","article-title":"Finite scalar quantization: VQ-VAE made simple","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Mentzer"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129353"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096009"},{"key":"ref41","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ball","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747575"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097001"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096528"},{"key":"ref45","article-title":"A high fidelity and low complexity neural audio coding","author":"Liu","year":"2023"},{"key":"ref46","volume-title":"Vector Quantization and Signal Compression","volume":"159","author":"Gersho","year":"1991"},{"key":"ref47","volume-title":"Theory and Applications of Digital Speech Processing","author":"Rabiner","year":"2011"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/18.42217"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/18.256489"},{"key":"ref50","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref54","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref56","article-title":"SUPERSEDED - CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref58","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448028"},{"key":"ref62","article-title":"Subjective evaluation of speech quality with a crowdsourcing appraoch","year":"2018"},{"key":"ref63","article-title":"Codec 2","author":"Rowe","year":"2024"},{"key":"ref64","article-title":"Definition of the opus audio codec","author":"Valin","year":"2012"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref66","article-title":"Lyra V2 - a better, faster, and more versatile speech codec","year":"2022"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/10874827\/10742547.pdf?arnumber=10742547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:37:39Z","timestamp":1738867059000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10742547\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":66,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3491575","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}