Please use this identifier to cite or link to this item: http://dspace.ctu.edu.vn/jspui/handle/123456789/10456
Title: Development of Vietnamese Speech synthesis System using Deep neural Networks
Authors: Nguyen, Van Thinh
Nguyen, Quoc Bao
Phan, Huy Kinh
Do, Van Hai
Keywords: Text-to-speech
Deep neural network
Hidden Markov model
Speech synthesis
Issue Date: 2018
Series/Report no.: Journal of Computer Science and Cybernetics;Vol.34(04) .- P.349–363
Abstract: In this paper, we present our first Vietnamese speech synthesis system based on deep neural networks. To improve the training data collected from the Internet, a cleaning method is proposed. The experimental results indicate that by using deeper architectures we can achieve better performance for the TTS than using shallow architectures such as hidden Markov model. We also present the effect of using different amounts of data to train the TTS systems. In the VLSP TTS challenge 2018, our proposed DNN-based speech synthesis system won the first place in all three subjects including naturalness, intelligibility, and MOS.
URI: http://dspace.ctu.edu.vn/jspui/handle/123456789/10456
ISSN: 1813-9663
Appears in Collections:Tin học và Điều khiển học (Journal of Computer Science and Cybernetics)

Files in This Item:
File Description SizeFormat 
_file_5.73 MBAdobe PDFView/Open
Your IP: 3.81.28.10


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.