Published in

Springer Verlag, Lecture Notes in Computer Science, p. 323-328

DOI: 10.1007/3-540-44805-5_43

Links

Tools

Export citation

Search in Google Scholar

Towards a Dynamic Adjustment of the Language Weight

Journal article published in 2001 by Georg Stemmer, Viktor Zeissler, Elmar Noth ORCID, Heinrich Niemann
This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Green circle
Preprint: archiving allowed
Upload
Green circle
Postprint: archiving allowed
Upload
Red circle
Published version: archiving forbidden
Policy details
Data provided by SHERPA/RoMEO

Abstract

Most speech recognition systems use a language weight to re- duce the mismatch between the language model and the acoustic models. Usually a constant value of the language weight is chosen for the whole test set. In this paper, we evaluate the possibility to adapt the language weight dynamically to the state of the dialogue or to the current utter- ance. Our experiments show, that the gain in performance, that can be achieved with a dynamic adjustment of the language weight on our data is very limited. This result is independent of the information source that is used for the adaption of the language weight.