12 search results - page 1 / 3 » Deep Belief Networks using discriminative features for phone... |
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fea...
INTERSPEECH
2010
12 years 11 months ago
2010
Recently, Deep Belief Networks (DBNs) have been proposed for phone recognition and were found to achieve highly competitive performance. In the original DBNs, only framelevel info...
CVPR
2011
IEEE
13 years 1 months ago
2011
IEEE
The most popular way to use probabilistic models in vision is first to extract some descriptors of small image patches or object parts using well-engineered features, and then to...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
In this paper, we extend the work done on integrating multilayer perceptron (MLP) networks with HMM systems via the Tandem approach. In particular, we explore whether the use of D...
JMLR
2012
11 years 7 months ago
2012
Motivated by the observation that coarse and fine resolutions of an image reveal different structures in the underlying visual phenomenon, we present a model based on the Deep B...