INVESTIGADORES
ALBORNOZ Enrique Marcelo
congresos y reuniones científicas
Título:
Spoken emotion recognition using deep learning
Autor/es:
ENRIQUE M. ALBORNOZ; MÁXIMO E. SÁNCHEZ-GUTIÉRREZ; FABIOLA MARTÍNEZ-LICONA; HUGO L. RUFINER; JOHN GODDARD-CLOSE
Lugar:
Pto. Vallarta, México
Reunión:
Congreso; 19th Iberoamerican Congress on Pattern Recognition (CIARP 2014); 2014
Institución organizadora:
The Mexican Association for Computer Vision, Neural Computing and Robotics (MACVNR) and Cinvestav (Unidad Guadalajara)
Resumen:
Spoken emotion recognition is a multidisciplinary research area that has received increasing attention over the last few years. In this paper, restricted Boltzmann machines and deep belief networks are used to classify emotions in speech. The motivation lies in the recent success reported using these alternative techniques in speech processing and speech recognition. This classifier is compared with a multilayer perceptron classifier, using spectral and prosodic characteristics. A well-known German emotional database is used in the experiments and two methodologies of cross-validation are proposed. Our experimental results show that the deep method achieves an improvement of 8.67% over the baseline in a speaker independent scheme.
