{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T15:00:19Z","timestamp":1767970819980,"version":"3.49.0"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688194","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"610-617","source":"Crossref","is-referenced-by-count":16,"title":["Multi-Stream HiFi-GAN with Data-Driven Waveform Decomposition"],"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":"Information Technology Center, Nagoya University,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":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(83)90013-0"},{"key":"ref38","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","author":"kim","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref33","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2173"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-414"},{"key":"ref37","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"kong","year":"2021","journal-title":"Proc ICLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1897"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415087"},{"key":"ref34","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"Proc ICLR"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref62","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc ICLR"},{"key":"ref61","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3051765"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref65","article-title":"On the variance of the adaptive learning rate and beyond","author":"liu","year":"2020","journal-title":"Proc ICLR"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.65"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-845"},{"key":"ref67","year":"1996","journal-title":"Methods for subjective determination of transmission quality"},{"key":"ref2","first-page":"125","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"Proc SSW9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref22","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref21","article-title":"Adversarial audio synthesis","author":"donahue","year":"2019","journal-title":"Proc ICLR"},{"key":"ref24","article-title":"High fidelity speech synthesis with adversarial networks","author":"bi?kowski","year":"2020","journal-title":"Proc ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref26","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639687"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/78.258122"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053915"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003956"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1288"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal Forced Aligner: Trainable text-speech alignment using Kaldi","author":"mcauliffe","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref55","first-page":"894","article-title":"Soft-DTW: a differentiable loss function for time-series","author":"cuturi","year":"2017","journal-title":"Proc ICML"},{"key":"ref54","article-title":"Pay less attention with lightweight and dynamic convolutions","author":"wu","year":"2019","journal-title":"Proc ICLR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref52","article-title":"LEAF: A learnable frontend for audio classification","author":"zeghidour","year":"2021","journal-title":"Proc ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1156"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1463"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3089565"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1984"},{"key":"ref16","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"rezende","year":"2015","journal-title":"Proc ICML"},{"key":"ref17","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref18","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"Proc ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref4","article-title":"End-to-end adversarial text-to-speech","author":"donahue","year":"2021","journal-title":"Proc ICLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413851"},{"key":"ref5","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"Proc ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-831"},{"key":"ref7","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"Proc ICML"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462237"},{"key":"ref9","first-page":"2415","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref46","article-title":"Audio super resolution using neural networks","author":"kuleshov","year":"2017","journal-title":"Proc ICLR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8269005"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639636"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414913"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1461"},{"key":"ref44","first-page":"13062","article-title":"A spectral energy distance for parallel speech synthesis","author":"gritsenko","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref43","article-title":"Deconvolution and checkerboard artifacts","volume":"1","author":"odena","year":"2016","journal-title":"Distillation"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688194.pdf?arnumber=9688194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:13Z","timestamp":1652733673000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688194","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}