{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T14:30:33Z","timestamp":1780756233996,"version":"3.54.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Japan Science, and Technology Agency"},{"DOI":"10.13039\/501100009023","name":"Precursory Research for Embryonic Science and Technology","doi-asserted-by":"publisher","award":["JPMJPR1657"],"award-info":[{"award-number":["JPMJPR1657"]}],"id":[{"id":"10.13039\/501100009023","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JST, CREST","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Grants-in-Aid for Scientific Research","award":["17H06101"],"award-info":[{"award-number":["17H06101"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3061245","type":"journal-article","created":{"date-parts":[[2021,2,23]],"date-time":"2021-02-23T21:15:09Z","timestamp":1614114909000},"page":"1134-1148","source":"Crossref","is-referenced-by-count":21,"title":["Quasi-Periodic WaveNet: An Autoregressive Raw Waveform Generative Model With Pitch-Dependent Dilated Convolution Neural Network"],"prefix":"10.1109","volume":"29","author":[{"given":"Yi-Chiao","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick Lumban","family":"Tobing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuhiro","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1121\/1.1912679"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-12"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269007"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref30","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1232"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172441"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462393"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1210"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-30"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1966.4841"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916020"},{"key":"ref20","article-title":"Deep voice 3: Scaling text to speech with convolutional sequence learning","author":"ping","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1672"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-986"},{"key":"ref50","first-page":"10\ufffd215","article-title":"Glow: Generative flow with invertible $1\\times 1$ convolutions","author":"kingma","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.29007\/s4t1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref56","article-title":"The CMU ARCTIC speech databases for speech synthesis research","author":"kominek","year":"2003"},{"key":"ref55","author":"wu","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1949.232969"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref52","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"0","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref10","first-page":"2415","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1982.1163960"},{"key":"ref12","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"oord","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref15","first-page":"3370","article-title":"FloWaveNet : A generative flow for raw audio","author":"kim","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-3"},{"key":"ref19","first-page":"7989","article-title":"The challenge of realistic music generation: Modelling raw audio at scale","author":"dieleman","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164910"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1966.tb01706.x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref8","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref7","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"0","journal-title":"Proc SSW9"},{"key":"ref49","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","author":"kingma","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1635"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1757"},{"key":"ref48","first-page":"1530","article-title":"Variational inference with normalizing flows","volume":"37","author":"rezende","year":"0","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref47","article-title":"NICE: Non-linear independent components estimation","author":"dinh","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1121\/1.1908614"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/78.80824"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461878"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.003"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09361096.pdf?arnumber=9361096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T20:00:23Z","timestamp":1639771223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9361096\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3061245","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}