{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T21:04:59Z","timestamp":1725656699892},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747419","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"861-865","source":"Crossref","is-referenced-by-count":1,"title":["Architecture for Variable Bitrate Neural Speech Codec with Configurable Computation Complexity"],"prefix":"10.1109","author":[{"given":"Tejas","family":"Jayashankar","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology"}]},{"given":"Thilo","family":"Koehler","sequence":"additional","affiliation":[{"name":"Facebook AI"}]},{"given":"Kaustubh","family":"Kalgaonkar","sequence":"additional","affiliation":[{"name":"Facebook AI"}]},{"given":"Zhiping","family":"Xiu","sequence":"additional","affiliation":[{"name":"Facebook AI"}]},{"given":"Jilong","family":"Wu","sequence":"additional","affiliation":[{"name":"Facebook AI"}]},{"given":"Ju","family":"Lin","sequence":"additional","affiliation":[{"name":"Facebook AI"}]},{"given":"Prabhav","family":"Agrawal","sequence":"additional","affiliation":[{"name":"Facebook AI"}]},{"given":"Qing","family":"He","sequence":"additional","affiliation":[{"name":"Facebook AI"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415120"},{"key":"ref12","first-page":"2410","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref13","article-title":"SoundStream: An end-to-end neural audio codec","author":"zeghidour","year":"2021","journal-title":"arXiv preprint arXiv 2107 03312"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1816"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632723"},{"key":"ref16","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","author":"razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Hierarchical quantized autoencoders","author":"williams","year":"2020","journal-title":"arXiv preprint arXiv 2002 03580"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1609"},{"key":"ref4","first-page":"80","article-title":"Codec 2 - Open source speech coding at 2400 bits\/s and below","author":"rowe","year":"2011","journal-title":"ARRL and TAPR Digital Communications Conference"},{"key":"ref3","article-title":"Sinusoidal coding","author":"mcaulay","year":"1995","journal-title":"Tech Rep"},{"key":"ref6","article-title":"Improving Opus low bit rate quality with neural speech synthesis","author":"skoglund","year":"2019","journal-title":"arXiv preprint arXiv 1905 03817"},{"key":"ref5","article-title":"Definition of the Opus audio codec","author":"valin","year":"2012","journal-title":"IETF"},{"key":"ref8","article-title":"WaveNet: A generative model for raw audio","author":"den oord","year":"2016","journal-title":"arXiv preprint arXiv 1609 03286"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/45.1890"},{"key":"ref9","article-title":"Neural discrete representation learning","author":"den oord","year":"2017","journal-title":"arXiv preprint arXiv 1711 00540"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref22","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"arXiv preprint arXiv 1910 06458"},{"key":"ref21","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv preprint arXiv 1711 05847"},{"key":"ref23","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"arXiv preprint arXiv 2010 00170"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747419.pdf?arnumber=9747419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:46Z","timestamp":1660594066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747419\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747419","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}