{"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":1780756234515,"version":"3.54.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682298","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"5916-5920","source":"Crossref","is-referenced-by-count":74,"title":["Neural Source-filter-based Waveform Model for Statistical Parametric Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Xin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Takaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Investigation of WaveNet for text-to-speech synthesis","author":"wang","year":"2018","journal-title":"Tech Rep 6 SIG Technical Reports"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1937.tb00766.x"},{"key":"ref12","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","author":"kingma","year":"2016","journal-title":"Proc NIPS"},{"key":"ref13","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","author":"lee","year":"2001","journal-title":"Proc NIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-488"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683791"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1227"},{"key":"ref17","first-page":"179","article-title":"XIMERA: A new TTS from ATR based on corpus-based technologies","author":"kawai","year":"2004","journal-title":"Proc SSW5"},{"key":"ref18","first-page":"1043","article-title":"Mel-generalized cepstral analysis a unified approach","author":"tokuda","year":"1994","journal-title":"Proc ICSLP"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref4","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"Proc ICLP"},{"key":"ref3","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"ref5","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":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164910"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1981.1171294"},{"key":"ref2","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv preprint arXiv 1609 09861"},{"key":"ref9","author":"graves","year":"2008","journal-title":"Supervised Sequence Labelling with Recurrent Neural Networks"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","first-page":"547","article-title":"Introducing CURRENT: The Munich open-source CUDA recurrent neural network toolkit","volume":"16","author":"weninger","year":"2015","journal-title":"The Journal of Machine Learning Research"},{"key":"ref22","first-page":"1","article-title":"A four-parameter model of glottal flow","volume":"4","author":"fant","year":"1985","journal-title":"STL-QPSR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.382141"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472653"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/29.1651"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682298.pdf?arnumber=8682298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:17:06Z","timestamp":1657855026000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682298","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}