A unified framework to incorporate speech and language information in spoken language processing

Authors:
Keh-Yih Su;Tung-Hui Chiang;Yi-Chung Lin
Affiliations:
Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan, R.O.C.;Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan, R.O.C.;Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan, R.O.C.
Venue:
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Year:
1992

Citing 2
Cited 0

Grammatical category disambiguation by statistical optimization

Computational Linguistics
Robustness and discrimination oriented speech recognition using weighted HMM and subspace projection approaches

ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

To enhance the performance of spoken language processing. a unified framework is proposed in this paper to integrate speech and language information together. This framework uses probabilistic formulation to characterize different language analyses generated from language processing module. As probabilistic formulations are used in both speech and language processing modules, information from both modules can be easily integrated. To further improve the performance, a discrimination and robustness oriented learning procedure is proposed to adjust the parameters of probabilistic formulations. Significant improvement has been observed in the task of dictating the utterance of reading Chinese computer manuals, which operates in a speaker dependent, isolated word mode.