38 search results - page 1 / 8 » Deep-structured hidden conditional random fields for phoneti... |
INTERSPEECH
2010
12 years 11 months ago
2010
We extend our earlier work on deep-structured conditional random field (DCRF) and develop deep-structured hidden conditional random field (DHCRF). We investigate the use of this n...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Hidden Conditional Random Fields(HCRF) is a very promising approach to model speech. However, because HCRF computes the score of a hypothesis by summing up linearly weighted featu...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
Phoneme posterior probabilities estimated using Multi-Layer Perceptrons (MLPs) are extensively used both as acoustic scores and features for speech recognition. In this paper we e...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
We present a new method for classification with structured
latent variables. Our model is formulated using the
max-margin formalism in the discriminative learning literature.
We...
CVPR
2006
IEEE
14 years 6 months ago
2006
IEEE
We introduce a discriminative hidden-state approach for the recognition of human gestures. Gesture sequences often have a complex underlying structure, and models that can incorpo...