Sciweavers

89 search results - page 12 / 18
» Discriminative semi-parametric trajectory model for speech r...
Sort
View
ICASSP
2009
IEEE
14 years 3 months ago
Training and adapting MLP features for Arabic speech recognition
Features derived from Multi-Layer Perceptrons (MLPs) are becoming increasingly popular for speech recognition. This paper describes various schemes for applying these features to ...
J. Park, Frank Diehl, M. J. F. Gales, Marcus Tomal...
ICASSP
2010
IEEE
13 years 8 months ago
Investigations on ensemble based unsupervised adaptation methods
We have previously proposed unsupervised cross-validation (CV) adaptation that introduces CV into an iterative unsupervised batch mode adaptation framework to suppress the influe...
Yu Kubota, Takahiro Shinozaki, Sadaoki Furui
CVPR
2001
IEEE
14 years 10 months ago
Constructing Facial Identity Surfaces in a Nonlinear Discriminating Space
Recognising face with large pose variation is more challenging than that in a fixed view, e.g. frontal-view, due to the severe non-linearity caused by rotation in depth, selfshadi...
Yongmin Li, Shaogang Gong, Heather M. Liddell
ICASSP
2008
IEEE
14 years 2 months ago
Discriminative feature selection for hidden Markov models using Segmental Boosting
We address the feature selection problem for hidden Markov models (HMMs) in sequence classification. Temporal correlation in sequences often causes difficulty in applying featur...
Pei Yin, Irfan A. Essa, Thad Starner, James M. Reh...
ICPR
2008
IEEE
14 years 2 months ago
Boosting Gaussian mixture models via discriminant analysis
The Gaussian mixture model (GMM) can approximate arbitrary probability distributions, which makes it a powerful tool for feature representation and classification. However, it su...
Hao Tang, Thomas S. Huang