The sound of my voice: speaker representation loss for target voice separation.

Seongkyu Mun Soyeon Choe Jaesung Huh Joon Son Chung

Published in: CoRR (2019)

Keyphrases

synthesized speech
text to speech
representation scheme
prosodic features
speech sounds
neural network
machine learning
genetic algorithm
feature representation
emotion recognition
fundamental frequency
voice recognition
voice and data services
interactive voice response