Voice Conversion for TTS Systems with Tuning on the Target Speaker Based on GMM.

Vadim Zahariev Elias Azarov Alexander A. Petrovsky

Published in: SPECOM (2017)

Keyphrases

gaussian mixture model
speaker recognition
text to speech
neural network
computer systems
building blocks
learning systems
complex systems
prosodic features
management system
distributed systems
speaker identification
voice activity detection