EMPHASIS: An Emotional Phoneme-based Acoustic Model for Speech Synthesis System.

Hao Li Yongguo Kang Zhenyu Wang

Published in: INTERSPEECH (2018)

Keyphrases

speech synthesis
speech recognition
text to speech
prosodic features
vocal tract
case study
artificial intelligence
databases
image processing
pattern recognition
speech corpus
real time
computer vision
face recognition
language model