{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:49:44Z","timestamp":1771703384561,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["2017-0-00072"],"award-info":[{"award-number":["2017-0-00072"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2021.3129353","type":"journal-article","created":{"date-parts":[[2021,11,19]],"date-time":"2021-11-19T20:36:00Z","timestamp":1637354160000},"page":"12-25","source":"Crossref","is-referenced-by-count":25,"title":["Scalable and Efficient Neural Speech Coding: A Hybrid Design"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4133-8158","authenticated-orcid":false,"given":"Kai","family":"Zhen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3396-1137","authenticated-orcid":false,"given":"Jongmo","family":"Sung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mi Suk","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungkwon","family":"Beack","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3513-8328","authenticated-orcid":false,"given":"Minje","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3406","article-title":"A real-time wideband neural vocoder at 1.6 kb\/s using LPCNet","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Valin","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1966.4841"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/89.397089"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804299"},{"key":"ref6","first-page":"1","article-title":"Combining parametric and waveform-matching coders for low bit-rate speech coding","volume-title":"Proc. 10th Eur. Signal Process. Conf.","author":"Stachurski","year":"2000"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861837"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179064"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178954"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2939"},{"key":"ref12","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oord","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref19","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref21","article-title":"Auto-encoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Kingma","year":"2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref24","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1816"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054347"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1975.1092759"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3039765"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dauphin","year":"2017"},{"key":"ref31","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Yu","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461819"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2876171"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056488"},{"key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref39","first-page":"1409","article-title":"Early developments of LPC speech coding techniques","volume-title":"Proc. Int. Conf. Spoken Lang. Process.","author":"Itakura","year":"1990"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1121\/1.424266"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/45.1890"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/72.3.573"},{"key":"ref43","article-title":"Wideband coding of speech at around 16 kbit\/s using adaptive multi-rate wideband","author":"G. 722.2","year":"2003"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.1983.1091516"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172448"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref47","article-title":"Method for the subjective assessment of intermediate quality levels of coding systems (MUSHRA)","year":"2003"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref50","article-title":"High-quality, low-delay music coding in the Opus codec","author":"Valin","year":"2013","journal-title":"Audio Eng. Soc. Convention 135"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2730"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09622124.pdf?arnumber=9622124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:10:01Z","timestamp":1705025401000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9622124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3129353","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}