Open access
2026
A Comparative Study of Audio-Language Models for Speech Emotion Recognition in Spanish
The hybrid approach outperforms standalone embedding-based classification across all evaluated models, showing that class-specific confidence-driven routing can improve the use of embedding-based predictions.
Jorge Gómez-Navalon, Rong-Hao Pan, Tomás Bernal-Beltrán et al.
· Computer Modeling in Enginee... · 0 citations