Empirical Evaluation of Deep Recurrent Deep Neural Networks Models for Speech Emotion Recognition for Real Time Applications
Book Chapter
Elsayed, N, Zekios, CL, ElSayed, Z et al. (2026). Empirical Evaluation of Deep Recurrent Deep Neural Networks Models for Speech Emotion Recognition for Real Time Applications
. 1801 LNNS 255-264. 10.1007/978-3-032-15784-3_19
Elsayed, N, Zekios, CL, ElSayed, Z et al. (2026). Empirical Evaluation of Deep Recurrent Deep Neural Networks Models for Speech Emotion Recognition for Real Time Applications
. 1801 LNNS 255-264. 10.1007/978-3-032-15784-3_19
Interpreting speech emotions and understanding emotion states has significantly increased interest in research to improve the quality of different services and advance human-computer interaction. Recurrent-based neural networks can be utilized to extract the spatial and temporal emotion patterns of speech. In this paper, we empirically evaluate different recurrent-based neural network capabilities for efficient and precise recognition of different emotion patterns in speech. Our empirical analysis and study focus on determining the optimal recurrent architecture for speech emotion recognition for real-time applications.
