{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:20:21Z","timestamp":1775229621402,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746698","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"881-885","source":"Crossref","is-referenced-by-count":10,"title":["Vocbench: A Neural Vocoder Benchmark for Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Ehab A.","family":"AlBadawy","sequence":"first","affiliation":[{"name":"University at Albany,State University of New York,USA"}]},{"given":"Andrew","family":"Gibiansky","sequence":"additional","affiliation":[{"name":"Facebook AI,USA"}]},{"given":"Qing","family":"He","sequence":"additional","affiliation":[{"name":"Facebook AI,USA"}]},{"given":"Jilong","family":"Wu","sequence":"additional","affiliation":[{"name":"Facebook AI,USA"}]},{"given":"Ming-Ching","family":"Chang","sequence":"additional","affiliation":[{"name":"University at Albany,State University of New York,USA"}]},{"given":"Siwei","family":"Lyu","sequence":"additional","affiliation":[{"name":"University at Buffalo,State University of New York,USA"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref31","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"veaux","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref11","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ArXiv"},{"key":"ref12","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"ICML"},{"key":"ref13","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"ArXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref15","article-title":"Parallel Wave-GAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","author":"yamamoto","year":"2020","journal-title":"ICASSP"},{"key":"ref16","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"chen","year":"2020","journal-title":"ICLRE"},{"key":"ref17","article-title":"DiffWave: A versatile diffusion model for audio synthesis","author":"kong","year":"2020","journal-title":"ICLRE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2835720"},{"key":"ref28","article-title":"Variational walkback: Learning a transition operator as a stochastic recurrent net","author":"goyal","year":"2017","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref27","article-title":"Deep unsupervised learning using nonequi-librium thermodynamics","author":"sohl-dickstein","year":"2015","journal-title":"ICML"},{"key":"ref3","article-title":"KLATTSTAT: Knowledge-based parametric speech synthesis","author":"anumanchipalli","year":"2010","journal-title":"Seventh ISCA Workshop"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref29","article-title":"The LJ speech dataset","author":"ito","year":"2017"},{"key":"ref5","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"ArXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.1999.7099996"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3056"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0095-4470(19)30745-4"},{"key":"ref20","first-page":"1","article-title":"Towards the next generation of web-based experiments: A case study assessing basic audio quality following the ITU-R recommendation BS. 1534 (MUSHRA)","author":"schoeffler","year":"2015","journal-title":"1st Web Audio Conference"},{"key":"ref22","article-title":"Fréchet audio distance: A metric for evaluating music enhancement algorithms","author":"kilgour","year":"2018","journal-title":"ArXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref24","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref23","article-title":"r9y9\/wavenet vocoder","author":"yamamoto","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref25","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746698.pdf?arnumber=9746698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:48Z","timestamp":1661199108000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746698","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}