{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:15:17Z","timestamp":1776885317564,"version":"3.51.2"},"reference-count":40,"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\/icassp49357.2023.10096007","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Framewise Wavegan: High Speed Adversarial Vocoder In Time Domain With Very Low Computational Complexity"],"prefix":"10.1109","author":[{"given":"Ahmed","family":"Mustafa","sequence":"first","affiliation":[{"name":"Amazon Web Services,Palo Alto,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Marc","family":"Valin","sequence":"additional","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":"Paris","family":"Smaragdis","sequence":"additional","affiliation":[{"name":"Amazon Web Services,Palo Alto,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mike","family":"Goodwin","sequence":"additional","affiliation":[{"name":"Amazon Web Services,Palo Alto,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Tan","year":"2021","journal-title":"A survey on neural speech synthesis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632770"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632750"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-430"},{"key":"ref6","author":"van den Oord","year":"2016","journal-title":"WaveNet: A Generative Model for Raw Audio"},{"key":"ref7","author":"Kalchbrenner","year":"2018","journal-title":"Efficient neural audio synthesis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2041"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1156"},{"key":"ref11","author":"Kong","year":"2020","journal-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746675"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref15","author":"Kong","year":"2020","journal-title":"Diffwave: A versatile diffusion model for audio synthesis"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-301"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632750"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2173"},{"key":"ref20","author":"Chung","year":"2014","journal-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling"},{"key":"ref21","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"International conference on machine learning","author":"Dauphin"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804299"},{"key":"ref23","first-page":"14910","article-title":"Mel-GAN: Generative Adversarial Networks for Conditional Waveform Synthesis","author":"Kumar","year":"2019","journal-title":"Advances in NeurIPS 32"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref25","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"Salimans","year":"2016","journal-title":"Advances in NeurIPS"},{"key":"ref26","article-title":"Open-source Multi-speaker Corpora of the English Accents in the British Isles","volume-title":"Proc. LREC","author":"Demirsahin"},{"key":"ref27","article-title":"Open-Source High Quality Speech Datasets for Basque, Catalan and Galician","volume-title":"Proc. SLTU and CCURL","author":"Kjartansson"},{"key":"ref28","article-title":"Crowdsourcing Latin American Spanish for Low-Resource Text-to-Speech","volume-title":"Proc. LREC","author":"Guevara-Rukoz"},{"key":"ref29","article-title":"Open-source Multi-speaker Speech Corpora for Building Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu Speech Synthesis Systems","volume-title":"Proc. LREC","author":"He"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-14"},{"key":"ref31","article-title":"Burmese Speech Corpus, Finite-State Text Normalization and Pronunciation Grammars with an Application to Text-to-Speech","volume-title":"Proc. LREC","author":"Oo"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1139"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1096"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref35","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-317"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-912"},{"key":"ref38","author":"Valin","year":"2007","journal-title":"The speex codec manual"},{"key":"ref39","year":"2018","journal-title":"Recommendation P.808: Subjective evaluation of speech quality with a crowdsourcing approach"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743729"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10096007.pdf?arnumber=10096007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:15:18Z","timestamp":1710404118000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096007","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}