Login / Signup
Statistical singing voice conversion with direct waveform modification based on the spectrum differential.
Kazuhiro Kobayashi
Tomoki Toda
Graham Neubig
Sakriani Sakti
Satoshi Nakamura
Published in:
INTERSPEECH (2014)
Keyphrases
</>
multiscale
statistical analysis
fundamental frequency
data driven
real time
statistical models
neural network
frequency domain
data structure
decision trees
information systems
statistical methods
hypothesis testing
emotion recognition
statistical measures
artificial intelligence
multi fractal