Deep neural network-based power spectrum reconstruction to improve quality of vocoded speech with limited acoustic parameters

Acoustical Science and Technology

Online ISSN : 1347-5177
Print ISSN : 1346-3969
ISSN-L : 0369-4232

ACOUSTICAL LETTERS

Deep neural network-based power spectrum reconstruction to improve quality of vocoded speech with limited acoustic parameters

Takuma Okamoto, Kentaro Tachibana, Tomoki Toda, Yoshinori Shiga, Hisashi Kawai

Author information

Keywords: Speech synthesis, Vocoder, Deep neural networks, Power spectrum

JOURNAL FREE ACCESS

2018 Volume 39 Issue 2 Pages 163-166

DOI https://doi.org/10.1250/ast.39.163

Details

Article 1st page

Content from these authors

© 2018 by The Acoustical Society of Japan

Favorites & Alerts

Related articles

Recently viewed articles

Predecessor

Journal of the Acoustical Society of Japan (E)

Top