{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:06:44Z","timestamp":1776881204350,"version":"3.51.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9415087","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6029-6033","source":"Crossref","is-referenced-by-count":9,"title":["Noise Level Limited Sub-Modeling for Diffusion Probabilistic Vocoders"],"prefix":"10.1109","author":[{"given":"Takuma","family":"Okamoto","sequence":"first","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University,Information Technology Center,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshinori","family":"Shiga","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2020","journal-title":"Proc ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054119"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.813579"},{"key":"ref30","first-page":"6729","article-title":"Tranformer-based text-to-speech with weighted forced attention","author":"okamoto","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref34","year":"1996","journal-title":"Methods for subjective determination of transmission quality"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref11","first-page":"3370","article-title":"FloWaveNet : A generative flow for raw audio","author":"kim","year":"2019","journal-title":"Proc ICML"},{"key":"ref12","article-title":"Non-autoregressive neural text-to-speech","author":"peng","year":"2020","journal-title":"Proc ICML"},{"key":"ref13","article-title":"WaveFlow: A compact flow-based model for raw audio","author":"ping","year":"2020","journal-title":"Proc ICML"},{"key":"ref14","first-page":"210","article-title":"WG-WaveNet: Real-time high-fidelity speech synthesis without GPU","author":"lee","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref15","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref16","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref18","article-title":"High fidelity speech synthesis with adversarial networks","author":"bi?kowski","year":"2020","journal-title":"Proc ICLR"},{"key":"ref19","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"2021","journal-title":"Proc ICLR"},{"key":"ref28","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","author":"song","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref4","first-page":"2415","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"0"},{"key":"ref27","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1156"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003956"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref8","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref7","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"rezende","year":"2015","journal-title":"Proc ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"Proc ICLR"},{"key":"ref1","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"Proc SSW9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref22","article-title":"Multi-band MelGAN: Faster waveform generation for highquality text-to-speech","author":"yang","year":"2021","journal-title":"Proc SLT"},{"key":"ref21","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref24","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"Proc ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref25","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021","journal-title":"Proc ICLR"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09415087.pdf?arnumber=9415087","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:48Z","timestamp":1659486048000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9415087\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9415087","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}