INVESTIGADORES
ALBORNOZ Enrique Marcelo
congresos y reuniones científicas
Título:
Robust Emotion Recognition using Bio-inspired Features
Autor/es:
ENRIQUE M. ALBORNOZ; DIEGO H. MILONE; HUGO L. RUFINER
Lugar:
San Carlos de Bariloche, Río Negro
Reunión:
Congreso; XV Reunión de Trabajo en Procesamiento de la Información y Control (RPIC); 2013
Institución organizadora:
Universidad Nacional de Río Negro
Resumen:
Several bio-inspired representations have been applied to artificial systems for speech processing. In this work, an auditory signal representation is used to obtain bio-inspired features of emotional speech signals. These features, together with other spectral and prosodic features, is used for emotion recognition under noise conditions. Multilayer perceptrons were trained as classifiers and results were compared to the well-known mel frequency cepstral coefficients with the same type of classifiers. Results show that using the proposed representations, it is possible to significantly improve the robustness of an emotion recognition system.
