IEEE - Institute of Electrical and Electronics Engineers, Inc. - State of the art discriminative training of subspace constrained Gaussian mixture models in big training corpora

ICASSP 2013 - IEEE International Conference on Acoustics, Speech and Signal Processing

Author(s): Jing Huang ; Peder A. Olsen ; Vaibhava Goel
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 May 2013
Conference Location: Vancouver, BC, Canada
Conference Date: 26 May 2013
Page(s): 6,945 - 6,949
ISBN (Electronic): 978-1-4799-0356-6
ISSN (Paper): 1520-6149
DOI: 10.1109/ICASSP.2013.6639008
Regular:

Discriminatively trained full-covariance Gaussian mixture models have been shown to outperform its corresponding diagonal-covariance models on large vocabulary speech recognition tasks. However,... View More

Advertisement