{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:20:54Z","timestamp":1775229654647,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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","award":["24ZC1100"],"award-info":[{"award-number":["24ZC1100"]}],"id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/msp.2024.3444318","type":"journal-article","created":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T19:47:33Z","timestamp":1735760853000},"page":"85-93","source":"Crossref","is-referenced-by-count":6,"title":["Neural Speech and Audio Coding: Modern AI technology meets traditional codecs"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3513-8328","authenticated-orcid":false,"given":"Minje","family":"Kim","sequence":"first","affiliation":[{"name":"University of Illinois at Urba-na-Champaign, Champaign, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0167-4628","authenticated-orcid":false,"given":"Jan","family":"Skoglund","sequence":"additional","affiliation":[{"name":"Google LLC, San Francisco, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3403\/bsenisoiec11172"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5.842996"},{"key":"ref3","year":"2003","journal-title":"Information TechnologyCoding of Audio-Visual ObjectsPart 3: AudioAmendment 1: Bandwidth Extension"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3403\/01060443"},{"key":"ref5","year":"2003","journal-title":"Wideband Coding of Speech at Around 16 Kbit\/s Using Adaptive Multi-Rate Wideband (AMR-WB)"},{"key":"ref6","year":"2011","journal-title":"Information Technology  MPEG Audio Technologies  Part 3: Unified Speech and Audio Coding"},{"key":"ref7","year":"2011","journal-title":"Transport of Unified Speech and Audio Coding (USAC)"},{"key":"ref8","article-title":"Codec for enhanced voice services (EVS); voice activity detection (VAD)","volume-title":"3GPP 3rd Generation Partnership Project (3GPP)","year":"2020"},{"key":"ref9","volume-title":"Definition of the opus audio codec","author":"Valin","year":"2012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref11","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. (NIPS)","author":"Agustsson","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3129994"},{"key":"ref13","volume-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023"},{"key":"ref14","first-page":"27,980","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Kumar","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref16","volume-title":"Codec 2 - Open source speech coding at 2400 bit\/s and below.","author":"Rowe","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-023-00274-x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tsa.2002.804299"},{"key":"ref22","year":"2015","journal-title":"Method for the Subjective Assessment of Intermediate Quality Levels of Coding Systems (MUSHRA)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096528"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2018.2887337"},{"key":"ref25","year":"2012","journal-title":"Wideband Embedded Extension for ITU-T G.711 Pulse Code Modulation"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04158-0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053113"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747733"},{"key":"ref30","volume-title":"Digital enhanced cordless telecommunications (DECT); study of super wideband codec in DECT for narrowband, wideband and super-wideband audio communication including options of low delay audio connections","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1515\/9783110873429"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1816"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3129353"},{"key":"ref34","first-page":"2410","article-title":"Efficient neural audio synthesis","volume":"80","author":"Kalchbrenner","year":"2018","journal-title":"Proc. Int. Conf. Mach. Learn. (ICML)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096077"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3277693"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096056"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2020.3039765"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2151"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/79\/10819667\/10819704.pdf?arnumber=10819704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T09:44:49Z","timestamp":1736588689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10819704\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":40,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/msp.2024.3444318","relation":{},"ISSN":["1053-5888","1558-0792"],"issn-type":[{"value":"1053-5888","type":"print"},{"value":"1558-0792","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}