HKUST Library Institutional Repository Banner

HKUST Institutional Repository >
Electronic and Computer Engineering  >
ECE Conference Papers >

Please use this identifier to cite or link to this item:
Title: A multi-path syllable to word decoder with language model optimization and automatic lexicon augmentation
Authors: Tang, Haijiang
Fung, Pascale N.
Keywords: Large vocabulary continuous speech recognition (LVCSR)
Multi-path search
Language model optimization
Automatic lexicon augmentation
Issue Date: 2000
Citation: Proceedings 6th International Conference of Spoken Language Processing (Interspeech 2000), October 16-20, 2000, Beijing, China
Abstract: Syllable to word decoding plays a very important role in Chinese large vocabulary continuous speech recognition (LVCSR). However, lack of word boundary and other characteristics of Chinese language prohibits the development of high quality language model decoder. In this paper, we present a multi-path search with language model optimization and automatic lexicon augmentation method to improve the accuracy of syllable to word decoding. The experiment result shows that our method achieves 34.76% character accuracy improvment over baseline performance.
Rights: We would like to give credit to International Speech Communication Association for granting us permission to repost this article.
Appears in Collections:HLTC Conference Papers
ECE Conference Papers

Files in This Item:

File Description SizeFormat
multi.pdfpre-published version451KbAdobe PDFView/Open

All items in this Repository are protected by copyright, with all rights reserved.