Improving speech understanding by incorporating database constraints and dialogue history

Author

Seide, Frank ; Rueber, Bernhard ; Kellner, Andreas

Author_Institution

Philips GmbH Res. Labs., Aachen, Germany

Volume

2

fYear

1996

fDate

3-6 Oct 1996

Firstpage

1017

Abstract

In the course of a (man-machine) dialogue, the system´s belief concerning the user´s intention is continuously being built up. Moreover, restricting the discourse to a narrow application domain further constrains the variety of possible user reactions. We show how these knowledge sources may be utilized in a stochastic framework to improve speech understanding. On field test data collected with our automatic exchange board prototype PADIS, a relative reduction of attribute errors by 27% was obtained

Keywords

data integrity; database management systems; human factors; interactive systems; speech intelligibility; speech processing; application domain; attribute errors; automatic exchange board prototype PADIS; database constraints; dialogue history; field test data; knowledge sources; man-machine dialogue; speech understanding; stochastic framework; user intention; user reactions; Computer errors; History; Information retrieval; Laboratories; Man machine systems; Natural languages; Prototypes; Speech recognition; Stochastic processes; Transaction databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607776

Filename

607776