{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T15:07:44Z","timestamp":1783955264162,"version":"3.55.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2021.3129994","type":"journal-article","created":{"date-parts":[[2021,11,23]],"date-time":"2021-11-23T21:38:58Z","timestamp":1637703538000},"page":"495-507","source":"Crossref","is-referenced-by-count":567,"title":["SoundStream: An End-to-End Neural Audio Codec"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6896-3987","authenticated-orcid":false,"given":"Neil","family":"Zeghidour","sequence":"first","affiliation":[{"name":"Research Google Inc., Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandro","family":"Luebs","sequence":"additional","affiliation":[{"name":"Research Google Inc., Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Omran","sequence":"additional","affiliation":[{"name":"Research Google Inc., Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Skoglund","sequence":"additional","affiliation":[{"name":"Research Google Inc., Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7682-6795","authenticated-orcid":false,"given":"Marco","family":"Tagliasacchi","sequence":"additional","affiliation":[{"name":"Research Google Inc., Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.326413"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413439"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF51394.2020.9443419"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632730"},{"key":"ref6","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415120"},{"key":"ref11","article-title":"Definition of the opus audio codec","author":"Valin","year":"2012"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"issue":"12","key":"ref13","first-page":"956","article-title":"The ISO\/MPEG Unified speech and audio coding standard - Consistent high quality for all content types and at all bit rates","volume":"61","author":"Neuendorf","year":"2013","journal-title":"J. Audio Eng. Soc."},{"key":"ref14","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"Mehri","year":"2017"},{"key":"ref15","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Oord","year":"2018"},{"key":"ref16","article-title":"Efficient neural audio synthesis","author":"Kalchbrenner","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref18","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref19","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853900"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1924"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462581"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-267"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2696307"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462049"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1980.1094577"},{"key":"ref30","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. 5th Berkeley Symp. Math. Statist. Probability","author":"MacQueen","year":"1967"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1984.1162229"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1985.13340"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref34","article-title":"Neural discrete representation learning","author":"Oord","year":"2017"},{"key":"ref35","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","author":"Razavi","year":"2019"},{"key":"ref36","article-title":"The challenge of realistic music generation: Modelling raw audio at scale","author":"Dieleman","year":"2018"},{"key":"ref37","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171604"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MP.2006.1664069"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.1990.117117"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1816"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632723"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414605"},{"key":"ref46","article-title":"Fast and accurate deep network learning by exponential linear units (ELUS)","author":"Clevert","year":"2015"},{"key":"ref47","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Baevski","year":"2020"},{"key":"ref48","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1563"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00652"},{"key":"ref52","article-title":"DDSP: Differentiable digital signal processing","author":"Engel","year":"2020"},{"key":"ref53","article-title":"A spectral energy distance for parallel speech synthesis","author":"Gritsenko","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref56","first-page":"486","article-title":"Freesound datasets: A platform for the creation of open audio datasets","volume-title":"Proc. 18th Int. Soc. Music Inf. Retrieval Conf.","author":"Fonseca","year":"2017"},{"key":"ref57","first-page":"387","article-title":"Evaluation of algorithms using games: The case of music tagging","volume-title":"Proc. 10th Int. Soc. Music Inf. Retrieval Conf.","author":"Law","year":"2009"},{"key":"ref58","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"ref59","article-title":"Recommendation B S.1534-1: Method for the subjective assessment of intermediate quality level of coding systems","year":"2001","journal-title":"Int. Telecommun. Union"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref61","article-title":"Perceptual objective listening quality assessment","volume":"863","year":"2018","journal-title":"Int. Telecomm. Union"},{"key":"ref62","first-page":"1","article-title":"ViSQOL: The virtual speech quality objective listener","volume-title":"Proc. Int. Workshop Acoust. Signal Enhancement","author":"Hines","year":"2012"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"ref64","article-title":"WebRTC 1.0: Real-time communication between browsers","year":"2019"},{"key":"ref65","doi-asserted-by":"crossref","DOI":"10.17487\/rfc7478","article-title":"Web real-time communication use cases and requirements","author":"Holmberg","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804299"},{"key":"ref67","article-title":"High-fidelity generative image compression","author":"Mentzer","year":"2020"},{"key":"ref68","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09625818.pdf?arnumber=9625818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:09:59Z","timestamp":1705025399000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9625818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3129994","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}