TalkNet: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis.

Stanislav Beliaev Boris Ginsburg

Published in: Interspeech (2021)

Keyphrases

autoregressive
random fields
pattern recognition
prior knowledge
probabilistic model
non stationary
language model
computer vision
similarity measure
super resolution
speech synthesis
gaussian markov random field