Module Comparison Of Transformer-Tts For Speaker Adaptation Based On Fine-Tuning.

Katsuki Inoue Sunao Hara Masanobu Abe

Published in: APSIPA (2020)

Keyphrases

fine tuning
viable alternative
fine tune
speaker adaptation
text to speech
fuzzy logic
fault diagnosis
domain specific
speech recognition
fine tuned
neural network
maximum likelihood