Login / Signup
Perceptual quality and modeling accuracy of excitation parameters in DLSTM-based speech synthesis systems.
Eunwoo Song
Frank K. Soong
Hong-Goo Kang
Published in:
ASRU (2017)
Keyphrases
</>
speech synthesis
perceptual quality
speech recognition
image quality
machine learning
computer vision
visual quality
human visual system
human perception
text to speech