View in EDS

Minimum Phone Error Training of Precision Matrix Models.

Saved in:
Bibliographic Details
Title: Minimum Phone Error Training of Precision Matrix Models.
Authors: Khe Chai Sim1,2 kcs23@eng.cam.ac.uk, Gales, Mark J. F.2,3 mjfg@eng.cam.ac.uk
Source: IEEE Transactions on Audio, Speech & Language Processing. May2006, Vol. 14 Issue 3, p882-889. 8p. 4 Charts.
Subjects: Speech processing systems, Speech perception, Gaussian processes, Density functionals, Sound recording & reproducing, Speech
Abstract: Gaussian mixture models (GMMs) are commonly used as the output density function for large-vocabulary continuous speech recognition (LVCSR) systems. A standard problem when using multivariate GMMs to classify data is how to accurately represent the correlations in the feature vector. Full covarianee matrices yield a good model, but dramatically increase the number of model parameters. Hence, diagonal covariance matrices are commonly used. Structured precision matrix approximations provide an alternative, flexible, and compact representation. Schemes in this category include the extended maximum likelihood linear transform and subspace for precision and mean models. This paper examines how these precision matrix models can be discriminatively trained and used on state-of-the-art speech recognition tasks. In particular, the use of the minimum phone error criterion is investigated. Implementation issues associated with building LVCSR systems are also addressed. These models are evaluated and compared using large vocabulary continuous telephone speech and broadcast news English tasks. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Audio, Speech & Language Processing is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Gaussian mixture models (GMMs) are commonly used as the output density function for large-vocabulary continuous speech recognition (LVCSR) systems. A standard problem when using multivariate GMMs to classify data is how to accurately represent the correlations in the feature vector. Full covarianee matrices yield a good model, but dramatically increase the number of model parameters. Hence, diagonal covariance matrices are commonly used. Structured precision matrix approximations provide an alternative, flexible, and compact representation. Schemes in this category include the extended maximum likelihood linear transform and subspace for precision and mean models. This paper examines how these precision matrix models can be discriminatively trained and used on state-of-the-art speech recognition tasks. In particular, the use of the minimum phone error criterion is investigated. Implementation issues associated with building LVCSR systems are also addressed. These models are evaluated and compared using large vocabulary continuous telephone speech and broadcast news English tasks. [ABSTRACT FROM AUTHOR]
ISSN:15587916
DOI:10.1109/TSA.2005.858062