Speech-Enabled Interfaces for Travel Information Systems with Large Grammars

This paper introduces three grammar-segmentation methods capable of handling the large grammar issues associated with producing a real-time speech-enabled VXML bus travel application for London. Large grammars tend to produce relatively slow recognition interfaces and this work shows how this limita...

Full description

Saved in:
Bibliographic Details
Published inApplications and Innovations in Intelligent Systems XIV pp. 207 - 220
Main Authors Zhao, Baoli, Allen, Tony, Bargiela, Andrzej
Format Book Chapter
LanguageEnglish
Published United Kingdom Springer London, Limited 2006
Springer London
Subjects
Artificial intelligence
Automatic Speech Recognition
Recognition Accuracy
Speech Recogniser
Speech Recognition
Wave File
Online AccessGet full text
ISBN9781846286650
1846286654
DOI10.1007/978-1-84628-666-7_16

Cover

More Information
Summary:This paper introduces three grammar-segmentation methods capable of handling the large grammar issues associated with producing a real-time speech-enabled VXML bus travel application for London. Large grammars tend to produce relatively slow recognition interfaces and this work shows how this limitation can be successfully addressed. Comparative experimental results show that the novel last-word recognition based grammar segmentation method described here achieves an optimal balance between recognition rate, speed of processing and naturalness of interaction.
ISBN:9781846286650
1846286654
DOI:10.1007/978-1-84628-666-7_16