Improving Speech Understanding By Incorporating Database Constraints And Dialogue History (1996)
| Venue: | In Proc. ICSLP |
| Citations: | 11 - 5 self |
BibTeX
@INPROCEEDINGS{Seide96improvingspeech,
author = {Frank Seide and Bernhard Rüber and Andreas Kellner},
title = {Improving Speech Understanding By Incorporating Database Constraints And Dialogue History},
booktitle = {In Proc. ICSLP},
year = {1996},
pages = {1017--1020}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
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. In this paper, we will 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% has been obtained.
Citations
| 26 | Stochastic Representation of Semantic Structure for Speech Understanding,” Speech Communication - Pieraccini, Levin - 1992 |
| 25 | A realtime prototype of an automatic inquiry system - Oerder, Aust - 1994 |
| 17 | PADIS ± An automatic telephone switchboard and directory information system - Kellner, Rueber, et al. - 1997 |
| 14 | Statistical Language Modeling Combining N-gram and Context-free Grammars - Meteer, Rohlicek |
| 13 | Phrase Bigrams for Continuous Speech Recognition - Giachin - 1995 |
| 12 | Experience with the Philips Automatic Train Timetable Information System - Aust, Oerder, et al. - 1994 |
| 9 | Word graphs: An ecient interface between continuous speech recognition and language understanding - Oerder, Ney - 1993 |
| 1 | A word-graph based N-best searchincontinuous speech recognition - Tran, Seide, et al. - 1996 |
