A spoken language inquiry system for automatic train timetable information

被引:9
作者
Aust, H
Oerder, M
Seide, F
Steinbiss, V
机构
[1] Philips GmbH Forschungslaboratorien, D-52021 Aachen
关键词
automatic inquiry system; speech recognition; speech understanding; natural language understanding; word graph; dialogue control; train timetable information;
D O I
10.1016/0165-5817(96)81588-9
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
This article describes the Philips automatic train timetable information system which enables the user to call up accurate information about train connections between 1200 German cities over the telephone. In contrast to most of the inquiry systems available so far, the caller can talk to our system in unrestricted, natural and fluent speech, very much like talking to a human operator. No instructions are given beforehand. The system consists of four main components: speech recognition, speech understanding, dialogue control, and speech output. They are separated into independent modules and executed sequentially. The speech recogniser creates a word graph from the spoken input. This word graph is then passed to the understanding component which computes the meaning, using an attributed stochastic context-free grammar. A dialogue manager analyses the results and either accesses the database or comes up with another question if necessary. The system has been made available to the general public in an ongoing field test, both to gather speech data and to evaluate its performance.
引用
收藏
页码:399 / 418
页数:20
相关论文
共 11 条
[1]  
ALLEN JF, 1992, P DARPA SPEECH NATUR, P5
[2]  
Aust Harald, 1995, ESCA WORKSH SPOK DIA, P121
[3]  
BLY B, 1990, P DARPA SPEECH NATUR, P136
[4]  
DEMMEL A, 1991, THESIS U KAISERSLAUT
[5]  
Fu K.S., 2019, APPL PATTERN RECOGNI
[6]  
GERBINO E, 1993, P INT C ACOUSTICS SP
[7]  
Hemphill C. T., 1990, SPEECH NATURAL LANGU
[8]  
MOORE R, 1992, P DARPA SPEECH NATUR, P61
[9]  
NEY H, 1992, P INT C ACOUSTICS SP
[10]  
OERDER M, 1993, P INT C ACOUSTICS SP