Effective Zero-Shot Multi-Speaker Text-to-Speech Technique Using Information Perturbation and a Speaker Encoder.

Chae-Woon Bang Chanjun Chun

Published in: Sensors (2023)

Keyphrases

text to speech
high quality
information sources
spatial information
prosodic features
neural network
prior knowledge
information sharing
information extraction
motion estimation
multilayer perceptron
information fusion
audio visual