{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T14:30:34Z","timestamp":1780756234530,"version":"3.54.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053202","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"7214-7218","source":"Crossref","is-referenced-by-count":4,"title":["WaveFFJORD: FFJORD-Based Vocoder for Statistical Parametric Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Ning-Qian","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","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"},{"key":"ref11","first-page":"10215","article-title":"Glow: Generative flow with invertible 1x1 convolutions","author":"kingma","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"6571","article-title":"Neural ordinary differential equations","author":"chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"FFJORD: Free-form continuous dynamics for scalable reversible generative models","author":"grathwohl","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref14","article-title":"NICE: Non-linear independent components estimation","author":"dinh","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref15","article-title":"Density estimation using real NVP","author":"dinh","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref16","first-page":"3370","article-title":"FloWaveNet : A generative flow for raw audio","author":"kim","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref17","first-page":"6790","article-title":"Blow: a single-scale hyperconditioned flow for non-parallel rawaudio voice conversion","author":"serr","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"The mathematical theory of optimal processes","author":"pontryagin","year":"1962"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/03610919008812866"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref6","first-page":"2410","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref5","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ISCA Speech Synthesis Workshop"},{"key":"ref8","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref7","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref2","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"ze","year":"2013","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref9","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.21437\/Interspeech.2017-314","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"2017","journal-title":"InterSpeech"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053202.pdf?arnumber=9053202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:25:22Z","timestamp":1656361522000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053202","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}