Hostname: page-component-586b7cd67f-dlnhk Total loading time: 0 Render date: 2024-11-25T19:30:04.614Z Has data issue: false hasContentIssue false
  • English
  • Français

A decision-theoretic framework for the evaluation of language models used in speech recognizers

Published online by Cambridge University Press:  10 November 2005

J. R. DELLER ,
K. H. DESAI  and
Y. P. YANG
J. R. DELLER
Affiliation:
Department of Electrical & Computer Engineering, Michigan State University, 2120 EB, East Lansing, MI 48824-1226, USA e-mail: [email protected], [email protected]
K. H. DESAI
Affiliation:
Department of Electrical & Computer Engineering, Michigan State University, 2120 EB, East Lansing, MI 48824-1226, USA e-mail: [email protected], [email protected]
Y. P. YANG
Affiliation:
Department of Electrical & Computer Engineering, Michigan State University, 2120 EB, East Lansing, MI 48824-1226, USA e-mail: [email protected], [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

An analytical method for design and performance analysis of language models (LM) is described, and an example interactive software tool based on the technique is demonstrated. The LM performance analysis does not require on-line simulation or experimentation with the recognition system in which the LM is to employed. By exploiting parallels with signal detection theory, a profile of the LM as a function of the design parameters is given in a set of curves analogous to a receiver-operating-characteristic display.

Type
Papers
Information
Natural Language Engineering , Volume 11 , Issue 4 , December 2005 , pp. 363 - 396
Copyright
2005 Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)