5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

An Integrated Language Modeling with N-Gram Model and WA Model for Speech Recognition

Shuwu Zhang, Taiyi Huang

National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China

As to traditional n-gram model, smaller n value is an inherent defect for estimating language probabilities in speech recognition, simply because that estimation could not be executed over farther word association but by means of short sequential word correlated information. This has an strong effect on the performance of speech recognition. This paper introduces an integrated language modeling with n-gram model and word association model (abbreviated as WA model). This model integrated two kind of joint probabilities, traditional n-gram probability and word association probability, to estimate actual output probability. WA model are based on a combined probability estimation of orderly word association without distant and strict sequential limitation. In addition, two kinds of local linguistic constraints have also been incorporated into n-gram estimation for smoothing date sparse and adjusting special language unit score locally. A substantial improvement for the performance of Chinese phonetic-to-text transcription in speech recognition has been obtained.

Full Paper

Bibliographic reference.  Zhang, Shuwu / Huang, Taiyi (1997): "An integrated language modeling with n-gram model and WA model for speech recognition", In EUROSPEECH-1997, 2699-2702.