{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T14:38:20Z","timestamp":1742395100534,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096528","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Low-Bitrate Redundancy Coding of Speech Using A Rate-Distortion-Optimized Variational Autoencoder"],"prefix":"10.1109","author":[{"given":"Jean-Marc","family":"Valin","sequence":"first","affiliation":[{"name":"Amazon Web Services,Palo Alto,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"B\u00fcthe","sequence":"additional","affiliation":[{"name":"Amazon Web Services,Palo Alto,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed","family":"Mustafa","sequence":"additional","affiliation":[{"name":"Amazon Web Services,Palo Alto,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Soft then hard: Rethinking the quantization in neural image compression","author":"guo","year":"2021","journal-title":"Proc ICML"},{"article-title":"Auto-encoding variational Bayes","year":"2013","author":"kingma","key":"ref12"},{"key":"ref15","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"bengio","year":"2013","journal-title":"arvix preprint arXiv 1308 3432"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3034501"},{"journal-title":"Recommendation P 808 Subjective evaluation of speech quality with a crowdsourcing approach","year":"2018","key":"ref31"},{"journal-title":"Recommendation P 800 Methods for Subjective Determination of Transmission Quality","year":"1996","key":"ref30"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414605"},{"key":"ref10","article-title":"SoundStream: An end-to-end neural audio codec","volume":"30","author":"zeghidour","year":"2021","journal-title":"Trans on Acoustics Speech and Signal Processing"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2665"},{"key":"ref2","article-title":"High-quality speech coding with SampleRNN","author":"klejsa","year":"2019","journal-title":"Proc International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref17","article-title":"Range encoding: An algorithm for removing redundancy from a digitised message","author":"nigel","year":"1979","journal-title":"Proc Video and Data Recording Conference"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/18.532878"},{"key":"ref19","article-title":"Open-source Multi-speaker Corpora of the English Accents in the British Isles","author":"demirsahin","year":"2020","journal-title":"Proc LREC"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1986.1057198"},{"key":"ref24","article-title":"Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-toSpeech","author":"oo","year":"2020","journal-title":"Proc LREC"},{"key":"ref23","article-title":"Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems","author":"he","year":"2020","journal-title":"Proc LREC"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1096"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1139"},{"key":"ref20","article-title":"Open-Source High Quality Speech Datasets for Basque, Catalan and Galician","author":"kjartansson","year":"2020","journal-title":"Proc SLTU and CCURL"},{"key":"ref22","article-title":"Crowdsourcing Latin American Spanish for Low-Resource Text-to-Speech","author":"guevara-rukoz","year":"2020","journal-title":"Proc LREC"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-14"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746103"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-903"},{"key":"ref9","article-title":"Neural discrete representation learning","volume":"30","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10829"},{"key":"ref3","article-title":"A real-time wideband neural vocoder at 1.6 kb\/s using LPCNet","author":"valin","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref6","first-page":"6716","article-title":"Definition of the Opus Audio Codec","author":"valin","year":"2012","journal-title":"RFC"},{"key":"ref5","first-page":"2198","article-title":"RTP payload for redundant audio data","author":"kouvelas","year":"1997","journal-title":"RFC"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096528.pdf?arnumber=10096528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T14:01:39Z","timestamp":1699884099000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096528","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}