Paper Info
Title
Controlling a HIFI with a continuous speech understanding system
Abstract
In this paper we present a speech understanding system that accepts continuous speech sentences as input to command a HIFI set. The string of words obtained from the recogniser is sent to the understanding system that tries to fill in a set of frames specifying the triplet (SUBSYSTEM, PARAMETER, VALUE). The understanding module follows the philosophy presented in (1). The triplets are finally translated into infrared commands by an actuator module to be sent to the HIFI set, composed by a radio, a three deck CD player and a two tape cassette recorder/player. All circumstances (understanding incompleteness, HIFI set status, result of the command execution) are confirmed back to the user via a text to speech system with substitutable-concept pattern-based generated messages. We have introduced a response module because some of the final users will be blind people, and because we are studying the possibility of establishing restricted dialogues with the users in order to complete or correct the commands. The understanding engine is based on semantic-like tagging, including "garbage" tag, and context-dependent rules for meaning extraction. One of the system options allows the application developer to follow the reasoning process of the system (as every understanding rule has an associated concept pattern), spoken by the speech generation module. The concepts for speech generation are randomly substituted with alternative expressions having the same meaning to achieve a certain degree of naturalness in the response speech.
Year
Venue
Keywords
1998
ICSLP
context dependent,text to speech,infrared,application development
Field
DocType
Citations 
Computer science,Speech recognition
Conference
3
PageRank 
References 
Authors
0.56
2
6
Name
Order
Citations
PageRank
ferreiros cols macasguarasa130.56
J. FERREIROS211214.84
José Colás310014.98
j maciasguarasa430.56
alba cecilia ruiz530.56
José Manuel Pardo615230.36