Login / Signup
Direct Modeling of Frequency Spectra and Waveform Generation Based on Phase Recovery for DNN-Based Speech Synthesis.
Shinji Takaki
Hirokazu Kameoka
Junichi Yamagishi
Published in:
INTERSPEECH (2017)
Keyphrases
</>
speech synthesis
speech recognition
prosodic features
phase difference
text to speech
data sets
data mining
modeling method
vocal tract
image sequences
hidden markov models
frequency domain
high throughput
hyperspectral images
preprocessing phase
power spectra