{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T22:14:05Z","timestamp":1769724845916,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683277","type":"proceedings-article","created":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T16:07:22Z","timestamp":1555430842000},"page":"735-739","source":"Crossref","is-referenced-by-count":91,"title":["Low Bit-rate Speech Coding with VQ-VAE and a WaveNet Decoder"],"prefix":"10.1109","author":[{"given":"Cristina","family":"G\u00e2rbacea","sequence":"first","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}]},{"given":"A\u00e4ron van","family":"den Oord","sequence":"additional","affiliation":[{"name":"DeepMind, London, UK"}]},{"given":"Yazhe","family":"Li","sequence":"additional","affiliation":[{"name":"DeepMind, London, UK"}]},{"given":"Felicia S C","family":"Lim","sequence":"additional","affiliation":[{"name":"Google, San Francisco, USA"}]},{"given":"Alejandro","family":"Luebs","sequence":"additional","affiliation":[{"name":"Google, San Francisco, USA"}]},{"given":"Oriol","family":"Vinyals","sequence":"additional","affiliation":[{"name":"DeepMind, London, UK"}]},{"given":"Thomas C","family":"Walters","sequence":"additional","affiliation":[{"name":"DeepMind, London, UK"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804299"},{"key":"ref11","article-title":"Codec 2-open source speech coding at 2400 bit\/s and below","author":"rowe","year":"2011","journal-title":"Tech Rep"},{"key":"ref12","first-page":"6306","article-title":"Neural discrete representation learning","volume":"30","author":"den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv preprint arXiv 1312 6114"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref15","year":"2001","journal-title":"Method for the Subjective Assessment of Intermediate Sound Quality (MUSHRA)"},{"key":"ref16","article-title":"Speex: A free codec for free speech","author":"valin","year":"2016","journal-title":"arXiv preprint arXiv 1602 00377"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1109\/ICASSP.1996.540325","article-title":"A 2.4 kbit\/s MELP coder candidate for the new US Federal standard","volume":"1","author":"mccree","year":"1996","journal-title":"Acoustics Speech and Signal Processing 1996 ICASSP-96 Conference Proceedings 1996 IEEE International Conference on"},{"key":"ref18","year":"1988","journal-title":"Pulse Code Modulation (PCM) of Voice Frequencies"},{"key":"ref19","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"arXiv preprint arXiv 1806 04558"},{"key":"ref4","article-title":"Real-time adaptive image compression","author":"rippel","year":"2017","journal-title":"arXiv preprint arXiv 1705 05823"},{"key":"ref3","article-title":"Soft-to-hard vector quantization for end-to-end learned compression of images and neural networks","volume":"abs 1704 648","author":"agustsson","year":"2017","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2604566"},{"key":"ref8","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"den oord","year":"2016","journal-title":"SSW"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953233"},{"key":"ref2","article-title":"End-to-end optimized image compression","volume":"abs 1611 1704","author":"ball\u00e9","year":"2016","journal-title":"CoRR"},{"key":"ref1","article-title":"Lossy image compression with compressive autoencoders","author":"theis","year":"2017","journal-title":"arXiv preprint arXiv 1703 00395"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref20","article-title":"Sample efficient adaptive text-to-speech","author":"chen","year":"2018","journal-title":"arXiv preprint arXiv 1809 10460"},{"key":"ref21","first-page":"800","year":"1996","journal-title":"Methods for subjective determination of transmission quality"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683277.pdf?arnumber=8683277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T18:29:28Z","timestamp":1755714568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683277","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}