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

Barra Chicote, Roberto; Fernández Martínez, Fernando; Lebai Lutfi, Syaheerah Binti; Lucas Cuesta, Juan Manuel; Macías Guarasa, Javier; Montero Martínez, Juan Manuel; San Segundo Hernández, Rubén y Pardo Muñoz, José Manuel (2009). Acoustic Emotion Recognition using Dynamic Bayesian Networks and Multi-Space Distributions. En: "10th Annual Conference of the International Speech Communication Association, Interspeech 2009", 06/09/2009 - 10/09/2009, Brighton, UK.

Descripción

Título: Acoustic Emotion Recognition using Dynamic Bayesian Networks and Multi-Space Distributions
Autor/es:
  • Barra Chicote, Roberto
  • Fernández Martínez, Fernando
  • Lebai Lutfi, Syaheerah Binti
  • Lucas Cuesta, Juan Manuel
  • Macías Guarasa, Javier
  • Montero Martínez, Juan Manuel
  • San Segundo Hernández, Rubén
  • Pardo Muñoz, José Manuel
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: 10th Annual Conference of the International Speech Communication Association, Interspeech 2009
Fechas del Evento: 06/09/2009 - 10/09/2009
Lugar del Evento: Brighton, UK
Título del Libro: Proceedings of 10th Annual Conference of the International Speech Communication Association, Interspeech 2009
Fecha: 2009
Materias:
Palabras Clave Informales: automatic emotion recognition, multi-space probability distribution, dynamic bayesian networks, emotion challenge.
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Ingeniería Electrónica
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (288kB) | Vista Previa

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 a considerable less number of features. In the 5-class case, we achieve a statistically significant 6.5% relative improvement

Más información

ID de Registro: 5575
Identificador DC: http://oa.upm.es/5575/
Identificador OAI: oai:oa.upm.es:5575
URL Oficial: http://www.isca-speech.org/archive/interspeech_2009/i09_0336.html
Depositado por: Memoria Investigacion
Depositado el: 23 Dic 2010 08:44
Ultima Modificación: 20 Abr 2016 14:21
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM