{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T19:49:45Z","timestamp":1771703385103,"version":"3.50.1"},"reference-count":41,"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.2024.3482972","type":"journal-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T17:36:46Z","timestamp":1729186606000},"page":"1441-1447","source":"Crossref","is-referenced-by-count":3,"title":["DRED: Deep REDundancy Coding of Speech Using a Rate-Distortion-Optimized Variational Autoencoder"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9883-6927","authenticated-orcid":false,"given":"Jean-Marc","family":"Valin","sequence":"first","affiliation":[{"name":"Xiph.Org Foundation, Jaffrey, NH, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9684-1567","authenticated-orcid":false,"given":"Jan","family":"B\u00fcthe","sequence":"additional","affiliation":[{"name":"Xiph.Org Foundation, Jaffrey, NH, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4820-8446","authenticated-orcid":false,"given":"Ahmed","family":"Mustafa","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Palo Alto, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1172-3654","authenticated-orcid":false,"given":"Michael","family":"Klingbeil","sequence":"additional","affiliation":[{"name":"Amazon Web Services, Palo Alto, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10829"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8682435"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"key":"ref5","article-title":"RTP payload for redundant audio data","author":"Kouvelas","year":"1997"},{"key":"ref6","article-title":"Definition of the opus audio codec","author":"Valin","year":"2012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096528"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3440956"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447962"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-903"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096077"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096007"},{"key":"ref14","first-page":"2021","article-title":"Chunked autoregressive GAN for conditional waveform synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Morrison"},{"key":"ref15","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Oord","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414605"},{"key":"ref18","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2013"},{"key":"ref19","first-page":"3920","article-title":"Soft then hard: Rethinking the quantization in neural image compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3034501"},{"key":"ref21","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/18.532878"},{"key":"ref23","article-title":"Range encoding: An algorithm for removing redundancy from a digitised message","volume-title":"Proc. Video Data Recording Conf.","author":"Nigel","year":"1979"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1986.1057198"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref27","first-page":"6532","article-title":"Open-source multi-speaker corpora of the english accents in the British isles","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Demirsahin","year":"2020"},{"key":"ref28","first-page":"21","article-title":"Open-source high quality speech datasets for Basque, Catalan and Galician","volume-title":"Proc. 1st Joint Workshop Spoken Lang. Technol. Under-Resourced Lang., Collaboration Comput. Under-Resourced Lang.","author":"Kjartansson","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-14"},{"key":"ref30","first-page":"6504","article-title":"Crowdsourcing Latin American Spanish for low-resource text-to-speech","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Guevara-Rukoz","year":"2020"},{"key":"ref31","first-page":"6494","article-title":"Open-source multi-speaker speech corpora for building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu speech synthesis systems","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"He","year":"2020"},{"key":"ref32","first-page":"6328","article-title":"Burmese speech corpus, finite-state text normalization and pronunciation grammars with an application to text-to-speech","volume-title":"Proc. 12th Lang. Resour. Eval. Conf.","author":"Oo","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1139"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1096"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref36","article-title":"Methods for subjective determination of transmission quality","year":"1996"},{"key":"ref37","article-title":"Subjective evaluation of speech quality with a crowdsourcing approach","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2665"},{"key":"ref39","article-title":"WebRTC audio codec and processing requirements","author":"Valin","year":"2016"},{"key":"ref40","article-title":"PLCMOSA data-driven non-intrusive metric for the evaluation of packet loss concealment algorithms","volume-title":"Proc. INTERSPEECH","author":"Diener","year":"2023"},{"key":"ref41","article-title":"Deep audio redundancy (DRED) extension for the opus codec","author":"Valin","year":"2024"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/10874827\/10720841.pdf?arnumber=10720841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:37:47Z","timestamp":1738867067000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10720841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":41,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3482972","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}