Recent Advances in Robust Speech Recognition Technology

by

Javier Ramírez, Juan Manuel Górriz

DOI: 10.2174/9781608051724111010
eISBN: 978-1-60805-172-4, 2011
ISBN: 978-1-60805-389-6



Indexed in: Scopus, EBSCO.

This E-book is a collection of articles that describe advances in speech recognition technology. Robustness in speech recognition refe...[view complete introduction]
US $
Buy Personal eBook
21
Order Library eBook
84
Order Printed Copy
*92
Order PDF + Printed Copy (Special Offer)
*102

*(Excluding Mailing and Handling)

🔒Secure Checkout Personal information is secured with SSL technology

Bayesian Networks and Discrete Observations for Robust Speech Recognition

- Pp. 133-140 (8)

Antonio Miguel, Alfonso Ortega and Eduardo Lleida

Abstract

Traditionally, in speech recognition, the hidden Markov model state emission probability distributions are usually associated to continuous random variables, by using Gaussian mixtures. Thus, the inter-feature dependence is not accurately modeled by the covariance matrix, since it only considers pairs of variables. The mixture is the part of the model which usually captures this information, but this is done in a loose and inefficient way. Graphical models provide a precise and simple mechanism to model the dependencies among two or more variables. We propose the use of discrete random variables as observations and graphical models to extract the internal dependence structure in the feature vectors. A method to estimate a graphical model with a constrained number of dependencies is shown in this chapter, which is a special kind of Bayesian network. Experimental results show that this method can be considered robust as compared to standard baseline systems.

Purchase Chapter  Book Details

Advertisement


Webmaster Contact: info@benthamscience.net Copyright © 2019 Bentham Science