Loading [MathJax]/extensions/MathMenu.js
Neural network based language models for highly inflective languages | IEEE Conference Publication | IEEE Xplore

Scheduled Maintenance: On Tuesday, May 20, IEEE Xplore will undergo scheduled maintenance from 1:00-5:00 PM ET (6:00-10:00 PM UTC). During this time, there may be intermittent impact on performance. We apologize for any inconvenience.

Neural network based language models for highly inflective languages


Abstract:

Speech recognition of inflectional and morphologically rich languages like Czech is currently quite a challenging task, because simple n-gram techniques are unable to cap...Show More

Abstract:

Speech recognition of inflectional and morphologically rich languages like Czech is currently quite a challenging task, because simple n-gram techniques are unable to capture important regularities in the data. Several possible solutions were proposed, namely class based models, factored models, decision trees and neural networks. This paper describes improvements obtained in recognition of spoken Czech lectures using language models based on neural networks. Relative reductions in word error rate are more than 15% over baseline obtained with adapted 4-gram backoff language model using modified Kneser-Ney smoothing.
Date of Conference: 19-24 April 2009
Date Added to IEEE Xplore: 26 May 2009
ISBN Information:

ISSN Information:

Conference Location: Taipei, Taiwan

Contact IEEE to Subscribe

References

References is not available for this document.