Title
Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks.
Abstract
A method for statistical parametric speech synthesis incorporating generative adversarial networks (GANs) is proposed. Although powerful deep neural networks techniques can be applied to artificially synthesize speech waveform, the synthetic speech quality is low compared with that of natural speech. One of the issues causing the quality degradation is an oversmoothing effect often observed in the...
Year
DOI
Venue
2018
10.1109/TASLP.2017.2761547
IEEE/ACM Transactions on Audio, Speech, and Language Processing
Keywords
DocType
Volume
Speech,Gallium nitride,Acoustics,Training,Hidden Markov models,Speech synthesis,Natural languages
Journal
26
Issue
ISSN
Citations 
1
2329-9290
12
PageRank 
References 
Authors
0.58
29
3
Name
Order
Citations
PageRank
Saito, Yuki1267.87
Shinnosuke Takamichi27522.08
Saruwatari, H.365290.81