Login / Signup
Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis.
Sang-Hoon Lee
Hyun-Wook Yoon
Hyeong-Rae Noh
Ji-Hoon Kim
Seong-Whan Lee
Published in:
AAAI (2021)
Keyphrases
</>
high fidelity
speech synthesis
speech recognition
real time
text to speech
medical image compression
speech signal
vocal tract
video conferencing
automatic speech recognition
pattern analysis
high quality
prosodic features
vector quantization
motion estimation
high resolution
optical flow
decision making