Voice Conversion Based on Probabilistic Parameter Transformation and Extended Inter-speaker Residual Prediction.

Zdenek Hanzlícek Jindrich Matousek

Published in: TSD (2007)

Keyphrases

prediction accuracy
prediction model
prediction algorithm
parameter values
prediction scheme
generative model
data driven
speaker recognition
parameter settings
conditional probabilities
audio visual
speech recognition
multi modal
speech synthesis
residual error
probabilistic model
synthesized speech