{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T09:03:36Z","timestamp":1753520616782,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461714","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"5299-5303","source":"Crossref","is-referenced-by-count":18,"title":["Text-to-Speech Synthesis Using STFT Spectra Based on Low-\/Multi-Resolution Generative Adversarial Networks"],"prefix":"10.1109","author":[{"given":"Yuki","family":"Saito","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","volume":"abs 1609 3499","author":"oord","year":"2016","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref11","volume":"abs 1612 7837","author":"mehri","year":"2016","journal-title":"Samplernn An unconditional end-to-end neural audio generation model"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953088"},{"key":"ref16","article-title":"Statistical parametric speech synthesis incorporating generative adversarial networks","volume":"abs 1709 8041","author":"saito","year":"2017","journal-title":"arXiv (preprint of IEEE\/ACM Transactions on Audio Speech and Language Processing)"},{"key":"ref17","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2522655"},{"key":"ref28","volume":"abs 1411 1784","author":"mirza","year":"2014","journal-title":"Conditional generative adversarial networks"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2551865"},{"key":"ref27","volume":"abs 1707 1670","author":"yang","year":"2017","journal-title":"Statistical parametric speech synthesis using generative adversarial networks under a multi-task learning framework"},{"key":"ref3","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref6","first-page":"1877","volume":"e99 d","author":"morise","year":"2016","journal-title":"WORLD a vocoder-based high-quality speech synthesis system for real-time applications"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref7","first-page":"93","article-title":"An overview of nitech hmm-based speech synthesis system for blizzard challenge 2005","author":"zen","year":"2005","journal-title":"Proc Inter-speech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref9","first-page":"1128","article-title":"Direct modeling of frequency spectra and waveform generation based on phase recovery for dnn-based speech synthesis","author":"takaki","year":"2017","journal-title":"Proc Inter-speech"},{"key":"ref1","first-page":"679","article-title":"Speech synthesis by rule using an optimal selection of non-uniform synthesis units","author":"sagisaka","year":"1988","journal-title":"Proc ICASSP"},{"key":"ref20","first-page":"5595","article-title":"Modulation spectrum compensation for hmm-based speech synthesis using line spectral pairs","author":"ling","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-962"},{"key":"ref21","first-page":"4910","article-title":"Generative adversarial network-based postfilter for statistical parametric speech synthesis","author":"kaneko","year":"2017","journal-title":"Proc ICA SSP"},{"key":"ref24","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref23","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc AISTATS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08461714.pdf?arnumber=8461714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:27:17Z","timestamp":1598221637000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461714\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461714","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}