ICASSP 2005, 30th IEEE International Conference on Acoustics, Speech, and Signal Processing, March 18-23, 2005- Philadelphia, USA
In this paper, an approach based on Variational Bayesian Feature Saliency (VBFS) for robust audio type classification is proposed. VBFS aims at finding the most discriminative features in Gaussian Mixture Models based recognition systems. VBFS is applied to capture inter-type and intra-type feature saliency for different audio type (music, background noise, wide band speech, narrow band speech, etc.) in order to increase model generality that's always poor in non-speechmodels. We show that inferring saliency for different audio type improves classifications. Experiments are run on Broadcast news 1996-Hub4.
Type:
Conférence
City:
Philadelphia
Date:
2005-03-18
Department:
Sécurité numérique
Eurecom Ref:
1568
Copyright:
© 2005 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
See also:
