Journal
COMPUTER SPEECH AND LANGUAGE
Volume 25, Issue 2, Pages 404-439Publisher
ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
DOI: 10.1016/j.csl.2010.06.003
Keywords
Speech recognition; Gaussian Mixture Model; Subspace Gaussian Mixture Model
Categories
Funding
- National Science Foundation [IIS-0833652]
- Google Research
- DARPA
- Johns Hopkins University Human Language Technology Center of Excellence
- Czech Ministry of Trade and Commerce [FR-TI1/034]
- Grant Agency of Czech Republic [102/08/0707]
- Czech Ministry of Education [MSM0021630528]
- European Community [213850]
Ask authors/readers for more resources
We describe a new approach to speech recognition, in which all Hidden Markov Model (HMM) states share the same Gaussian Mixture Model (GMM) structure with the same number of Gaussians in each state. The model is defined by vectors associated with each state with a dimension of, say, 50, together with a global mapping from this vector space to the space of parameters of the GMM. This model appears to give better results than a conventional model, and the extra structure offers many new opportunities for modeling innovations while maintaining compatibility with most standard techniques. (C) 2010 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available