Geintra

Departamento de electronica Universidad de Alcala

Líneas de investigación

Accede a información sobre la estructura de la actividad investigadora de Geintra.

Trabaja con nosotros

Accede a nuestra oferta actual de becas, tesis doctorales, contratos y trabajos fin de carrera.

Contacta con el grupo

Si desea contactar con nosotros, puede usar varios medios.

    Acoustic Emotion Recognition using Dynamic Bayesian Networks and Multi-Space Distributions

    TítuloAcoustic Emotion Recognition using Dynamic Bayesian Networks and Multi-Space Distributions
    Tipo de publicaciónConference Paper
    Año de publicación2009
    AutoresBarra-Chicote, R, Fernandez, F, Lutfi, SL, Lucas-Cuesta, JM, Macias-Guarasa, J, Montero, JM, San-Segundo, R, Pardo, JM
    Idioma de publicaciónEnglish
    Conference Name10th Annual Conference of the Internacional Speech Communication Association (INTERSPEECH 2009)
    Páginas336-339
    EditorialInternacional Speech Communication Association
    Conference LocationBrighton, U.K.
    Fecha de publicación09/2009
    Palabras claveautomatic emotion recognition, dynamic bayesian networks, emotion challenge, multi-space probability distribution
    Resumen

    In this paper we describe the acoustic emotion recognition
    system built at the Speech Technology Group of the Universidad
    Politecnica de Madrid (Spain) to participate in the INTERSPEECH
    2009 Emotion Challenge. Our proposal is based on
    the use of a Dynamic Bayesian Network (DBN) to deal with
    the temporal modelling of the emotional speech information.
    The selected features (MFCC, F0, Energy and their variants) are
    modelled as different streams, and the F0 related ones are integrated
    under a Multi Space Distribution (MSD) framework, to
    properly model its dual nature (voiced/unvoiced). Experimental
    evaluation on the challenge test set, show a 67.06% and 38.24%
    of unweighted recall for the 2 and 5-classes tasks respectively.
    In the 2-class case, we achieve similar results compared with
    the baseline, with 8.5 times less features. In the 5-class case, we
    achieve a statistically significant 6.5% relative improvement.

    AdjuntoTamaño
    p46039.pdf106.73 KB