Speech Emotion Recognition Using Label Smoothing Based on Neutral and Anger Characteristics.

Ryotaro Nagase Takahiro Fukumori Yoichi Yamashita

Published in: LifeTech (2022)

Keyphrases

emotion recognition
emotional state
facial expressions
text to speech synthesis
speech recognition
emotional speech
multi label
noisy environments
text to speech
physiological signals
video sequences
smoothing methods
affective computing