Combining stochastic and linguistic language models for recognition of spontaneous speech

Authors:
W. Eckert;F. Gallwitz;H. Niemann
Affiliations:
Lehrstuhl fur Mustererkennung, Erlangen-Nurnberg Univ., Germany;Sch. of Comput. Sci., Carnegie Mellon Univ., Pittsburgh, PA, USA;Interactive Syst. Lab., Carnegie Mellon Univ., Pittsburgh, PA, USA
Venue:
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 01
Year:
1996

Citing 0
Cited 4

Towards a Dynamic Adjustment of the Language Weight

TSD '01 Proceedings of the 4th International Conference on Text, Speech and Dialogue
The Utility of Semantic-Pragmatic Information and Dialogue-State for Speech Recognition in Spoken Dialogue Systems

TDS '00 Proceedings of the Third International Workshop on Text, Speech and Dialogue
Dialogue act modeling for automatic tagging and recognition of conversational speech

Computational Linguistics
A speech understanding framework that uses multiple language models and multiple understanding models

NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a new approach of combining stochastic language models and traditional linguistic models to enhance the performance of our spontaneous speech recognizer. We compile arbitrary large linguistic context dependencies into a category based bigram model which allows us to use a standard beam-search driven forward Viterbi algorithm for real time decoding. Since this recognizer is used in a dialog system, the information about the last system utterance is used to build dialogstep dependent language models. This setup is verified and tested on our corpus of spontaneous speech utterances collected with our dialog system. Experimental results show a significant reduction of word error rate.