Genevieve Gorrell
Linköping University, Sweden
Download article
Published in: MUM 2003. Proceedings of the 2nd International Conference on Mobile and Ubiquitous Multimedia
Linköping Electronic Conference Proceedings 11:12, p. 67-71
Published: 2003-12-10
ISBN:
ISSN: 1650-3686 (print), 1650-3740 (online)
Increasing use of mobile devices for information access brings with it a demand for robust speech recognition. An important way in which speech recognition system performance can be improved is through use of dialogue strategies to handle the situation in which the system fails to recognise the user’s utterance. In the work described here; the case is made for combining multiple speech recognisers and appropriate dialogue strategies to handle poor recognition results. Two implemented systems are discussed as examples.
2003. Proceedings of Error-Handling in Spoken Dialogue Systems. Eurospeech satellite event.
Gorrell; G.; Lewin; I.; and Rayner; M. 2002. Adding intelligent help to mixed initiative spoken dialogue systems. In Proceedings of ICSLP.
Gorrell; G. 2003. Using statistical language modelling to identify new vocabulary in a grammar-based speech recognition system. In Proceedings of Eurospeech.
Knight; S.; Gorrell; G.; Rayner; M.; Milward; D.; Koeling; R.; and Lewin; I. 2001. Comparing grammar-based and robust approaches to speech understanding: a case study. In Proceedings of Eurospeech 2001; 1779–1782.
Nuance. 2002. http://www.nuance.com. as of 15 March 2002.
RuleQuest. 2002. http://www.rulequest.com. as of 15 Mar 2002.
