{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:16:27Z","timestamp":1757542587134,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414444","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"6044-6048","source":"Crossref","is-referenced-by-count":21,"title":["Universal Neural Vocoding with Parallel Wavenet"],"prefix":"10.1109","author":[{"given":"Yunlong","family":"Jiao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Gabrys","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgi","family":"Tinchev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bartosz","family":"Putrycz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Korzekwa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Viacheslav","family":"Klimkov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"14881","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2880284"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"ref14","first-page":"30","article-title":"Multispeaker neural vocoder","author":"barbany","year":"2018","journal-title":"Fourth International Conference on IberSPEECH"},{"key":"ref15","article-title":"Speaker-adaptive neural vocoders for statistical parametric speech synthesis systems","volume":"abs 1811 3311","author":"song","year":"2018","journal-title":"CoRR"},{"key":"ref16","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"gibiansky","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1109\/ASRU.2017.8269007","article-title":"An investigation of multi-speaker training for wavenet vocoder","author":"hayashi","year":"2017","journal-title":"ASRU 2017 - IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1424"},{"key":"ref19","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"ICLR International Conference on Learning Representations"},{"key":"ref4","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","volume":"abs 1703 10135","author":"wang","year":"2017","journal-title":"CoRR"},{"key":"ref3","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","author":"arik","year":"2017","journal-title":"Proceedings of the ICML International Conference on Machine Learning"},{"key":"ref6","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"The 9th ISCA Speech Synthesis Workshop"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref8","first-page":"3915","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"Proceedings of the ICML International Conference on Machine Learning"},{"key":"ref7","first-page":"2415","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proceedings of the ICML International Conference on Machine Learning"},{"key":"ref2","article-title":"End-to-end adversarial text-to-speech","volume":"abs 2006 3575","author":"donahue","year":"2020","journal-title":"CoRR"},{"key":"ref1","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref9","first-page":"3617","article-title":"Waveglow: A flow-based generative network for speech synthesis","author":"prenger","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLR International Conference on Learning Representations"},{"year":"2020","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"year":"2020","key":"ref24"},{"journal-title":"International Telecommunication Union Geneva","article-title":"BS. 1534-1. method for the subjective assessment of intermediate sound quality (MUSHRA)","year":"2001","key":"ref23"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414444.pdf?arnumber=9414444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:50Z","timestamp":1652182850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414444","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}