15 search results - page 1 / 3 » Learning non-parametric models of pronunciation |
ICML
1999
IEEE
14 years 8 months ago
1999
IEEE
We present a learning algorithm for non-parametric hidden Markov models with continuous state and observation spaces. All necessary probability densities are approximated using sa...
CA
2003
IEEE
14 years 22 days ago
2003
IEEE
This paper presents an efficient method of learning motion control for autonomous animated characters. The method uses a non parametric learning approach which identifies non line...
AAAI
2008
13 years 9 months ago
2008
Matrix factorization algorithms are frequently used in the machine learning community to find low dimensional representations of data. We introduce a novel generative Bayesian pro...
ACL
2012
11 years 9 months ago
2012
We address the problem of learning the mapping between words and their possible pronunciations in terms of sub-word units. Most previous approaches have involved generative modeli...
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
As more data becomes available for a given speech recognition task, the natural way to improve recognition accuracy is to train larger models. But, while this strategy yields mode...