Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis.

Xin Wang Junichi Yamagishi

Published in: SSW (2019)

Keyphrases

mathematical model
probabilistic model
formal model
objective function
statistical model
neural network
genetic algorithm
cost function
edge detection
maximum likelihood
parameter estimation
neural network model
signal to noise ratio
neural model