Speech Emotion Recognition using Time-frequency Random Circular Shift and Deep Neural Networks
Langue
en
Communication dans un congrès avec actes
Ce document a été publié dans
Speech Prosody 2022, 2022-05-23, Lisbonne.
Résumé en anglais
This paper addresses the problem of emotion recognition from a speech signal. Thus, we investigate a data augmentation technique based on circular shift of the input time-frequency representation which significantly enhances ...Lire la suite >
Mots clés en anglais
Speech Emotion Recognition (SER)
Deep Convolutional Neural Networks
Time-frequency
Random Circular Shift (RCS)