{"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":1780756234237,"version":"3.54.1"},"reference-count":67,"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":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"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.2021.3051765","type":"journal-article","created":{"date-parts":[[2021,1,14]],"date-time":"2021-01-14T22:40:12Z","timestamp":1610664012000},"page":"792-806","source":"Crossref","is-referenced-by-count":24,"title":["Quasi-Periodic Parallel WaveGAN: A Non-Autoregressive Raw Waveform Generative Model With Pitch-Dependent Dilated Convolution Neural Network"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4390-1354","authenticated-orcid":false,"given":"Yi-Chiao","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8782-4093","authenticated-orcid":false,"given":"Tomoki","family":"Hayashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-1279","authenticated-orcid":false,"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461878"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462393"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1232"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref30","first-page":"13","article-title":"Deep neural network based real-time speech vocoder with periodic and aperiodic inputs","author":"oura","year":"0","journal-title":"Proc SSW10"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461332"},{"key":"ref36","first-page":"712","article-title":"An investigation of multi-speaker training for WaveNet vocoder","author":"hayashi","year":"0","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref35","first-page":"1118","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref34","article-title":"Quasi-periodic WaveNet: An autoregressive raw waveform generative model with pitch-dependent dilated convolution neural network","author":"wu","year":"0","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref62","author":"wu","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.003"},{"key":"ref63","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013","journal-title":"arXiv 1308 0850 [cs]"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref64","article-title":"Neural turing machines","author":"graves","year":"2014","journal-title":"arXiv 1410 5401"},{"key":"ref27","article-title":"High fidelity speech synthesis with adversarial networks","author":"bi\u2019nkowski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref65","first-page":"1462","article-title":"DRAW: A recurrent neural network for image generation","author":"gregor","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref66","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref29","article-title":"Multi-band MelGAN: Faster waveform generation for high-quality text-to-speech","author":"yang","year":"0","journal-title":"Proc SLT"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"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","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3188"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2970241"},{"key":"ref21","article-title":"HooliGAN: Robust, high quality neural vocoding","author":"mccarthy","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1965"},{"key":"ref26","first-page":"910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume":"14","author":"kumar","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref51","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref59","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref58","first-page":"195","article-title":"The voice conversion challenge 2018: Promoting development of parallel and nonparallel methods","author":"lorenzo-trueba","year":"0","journal-title":"Proc Odyssey"},{"key":"ref57","article-title":"The CMU ARCTIC speech databases for speech synthesis research","author":"kominek","year":"0"},{"key":"ref56","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":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172441"},{"key":"ref53","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"maas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref52","article-title":"DDSP: Differentiable digital signal processing","author":"engel","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"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","first-page":"1138","article-title":"Statistical voice conversion with WaveNet-based waveform generation","author":"kobayashi","year":"0","journal-title":"Proc INTERSPEECH"},{"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 Represent"},{"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\/ICASSP40776.2020.9053202"},{"key":"ref17","first-page":"3394","article-title":"Generative adversarial network-based glottal waveform model for statistical parametric speech synthesis","author":"bollepalli","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683271"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1966.tb01706.x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164910"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1172250"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref46","first-page":"3535","article-title":"Quasi-periodic parallel WaveGAN vocoder: A non-autoregressive pitch dependent dilated convolution model for parametric speech generation","author":"wu","year":"0","journal-title":"Proc Interspeech 2020"},{"key":"ref45","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/89.397089"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1982.1163960"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.29007\/bw9p"},{"key":"ref41","first-page":"219","article-title":"NU voice conversion system for the voice conversion challenge 2018","author":"tobing","year":"0","journal-title":"Proc Odyssey"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984007"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1210"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09324976.pdf?arnumber=9324976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T11:27:44Z","timestamp":1643282864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9324976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3051765","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}