Please use this identifier to cite or link to this item:

Dealing with Multilinguality in a Spoken Language Query Translator

Authors Fung, Pascale N.
Shi, Bertram E.
Wu, Dekai
Lam, Wai Bun
Wong, Shuen Kong
Issue Date 1997
Source Proceedings ACL/EACL '97 workshop on spoken language translation, Madrid, Spaing , 7-12 July 1997, p. 40-47
Summary In this paper, we examine three issues concerning the robustness of multilingual speech interfaces for spoken language translation systems: accent differences, mixed language input, and the use of common feature sets for HMM-based speech recognizers for English and Cantonese. From the results of our preliminary experiments, we find that accent difference causes recognizers performance to degrade. For mixed language input, we found out that a straight forward implementation of a mixed language model-based speech recognizer performs less well than the concatenation of pure language recognizers due to the increase in recognition candidate numbers. Finally, our experimental results show that the Cantonese recognizer has a lower recognition rate on the average than the English recognizer despite a common feature set, parameter set, and common algorithm.
Language English
Format Conference paper
Files in this item:
File Description Size Format
slt97camera1.pdf 262665 B Adobe PDF