{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T03:50:11Z","timestamp":1784346611104,"version":"3.55.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JST CREST","award":["JPMJCR18A6"],"award-info":[{"award-number":["JPMJCR18A6"]}]},{"name":"MEXT KAKENHI","award":["19K24371"],"award-info":[{"award-number":["19K24371"]}]},{"name":"MEXT KAKENHI","award":["16H06302"],"award-info":[{"award-number":["16H06302"]}]},{"name":"MEXT KAKENHI","award":["16K16096"],"award-info":[{"award-number":["16K16096"]}]},{"name":"MEXT KAKENHI","award":["17H04687"],"award-info":[{"award-number":["17H04687"]}]},{"name":"MEXT KAKENHI","award":["18H04120"],"award-info":[{"award-number":["18H04120"]}]},{"name":"MEXT KAKENHI","award":["18H04112"],"award-info":[{"award-number":["18H04112"]}]},{"name":"MEXT KAKENHI","award":["18KT0051"],"award-info":[{"award-number":["18KT0051"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2019.2956145","type":"journal-article","created":{"date-parts":[[2019,11,27]],"date-time":"2019-11-27T22:45:30Z","timestamp":1574894730000},"page":"402-415","source":"Crossref","is-referenced-by-count":90,"title":["Neural Source-Filter Waveform Models for Statistical Parametric Speech Synthesis"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8246-0606","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Takaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3955","authenticated-orcid":false,"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1121\/1.424676"},{"key":"ref38","first-page":"1448","article-title":"Perceptual importance of the phase related information in speech","author":"saratxaga","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref33","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","author":"lee","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/29.1651"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168385"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1121\/1.397860"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1037\/h0020279"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1177\/002383096200500401"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-488"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461852"},{"key":"ref28","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"rezende","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462237"},{"key":"ref29","article-title":"Investigations of real-time neural vocoders with fundamental frequency and Mel-cepstra","author":"okamoto","year":"0","journal-title":"Proc Spring Meet Acoustical Soc Japan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1635"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref24","article-title":"LP-WaveNet: Linear prediction-based WaveNet speech synthesis","author":"hwang","year":"2018","journal-title":"arXiv 1811 11913"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref25","first-page":"2410","article-title":"Efficient neural audio synthesis","volume":"80","author":"kalchbrenner","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","first-page":"179","article-title":"XIMERA: A new TTS from ATR based on corpus-based technologies","author":"kawai","year":"0","journal-title":"Proc IEEE Workshop Speech Synthesis"},{"key":"ref51","article-title":"The NII speech synthesis entry for Blizzard Challenge 2016","author":"juvela","year":"0","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref59","article-title":"Fast WaveNet generation algorithm","author":"paine","year":"2016","journal-title":"arXiv 1611 09482"},{"key":"ref58","first-page":"359","article-title":"Thrust: A productivity-oriented library for CUDA","author":"bell","year":"2011","journal-title":"GPU Computing Gems Jade Edition"},{"key":"ref57","first-page":"547","article-title":"Introducing CURRENT: The Munich open-source CUDA recurrent neural network toolkit","volume":"16","author":"weninger","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1227"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref52","first-page":"1043","article-title":"Mel-generalized cepstral analysis a unified approach","author":"tokuda","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472655"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1144"},{"key":"ref40","article-title":"Supervised Sequence Labelling with Recurrent Neural Networks","author":"graves","year":"2008"},{"key":"ref12","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"ref14","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"0","journal-title":"Proc IEEE Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461878"},{"key":"ref16","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","author":"kingma","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref18","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","first-page":"3330","article-title":"Sequence-to-sequence neural net models for grapheme-to-phoneme conversion","author":"yao","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-17"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828650"},{"key":"ref8","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref7","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCT.1972.1083419"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953087"},{"key":"ref46","article-title":"Harmonic plus noise models for speech, combined with statistical methods, for speech and speaker modification","author":"stylianou","year":"1996"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319365"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/89.397089"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1121\/1.382141"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1937.tb00766.x"},{"key":"ref41","article-title":"Investigation of WaveNet for text-to-speech synthesis","author":"wang","year":"2018"},{"key":"ref44","first-page":"231","article-title":"Hybrid sinusoidal modeling of speech without voicing decision","author":"abrantes","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/08915761.pdf?arnumber=8915761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:31:23Z","timestamp":1651080683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8915761\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2956145","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}