Improving speech recognition on a mobile robot platform through the use of top-down visual queues

Files in This Item:
File Description SizeFormat 
P181-Ross,O¿Donoghue,O¿Hare-03.pdf12.14 kBAdobe PDFDownload
Title: Improving speech recognition on a mobile robot platform through the use of top-down visual queues
Authors: Ross, Robert
O'Donoghue, R. P. S.
O'Hare, G. M. P. (Greg M. P.)
Permanent link: http://hdl.handle.net/10197/4530
Date: 9-Aug-2003
Abstract: In many real-world environments, Automatic Speech Recognition (ASR) technologies fail to provide adequate performance for applications such as human robot dialog. Despite substantial evidence that speech recognition in humans is performed in a top-down as well as bottom-up manner, ASR systems typically fail to capitalize on this, instead relying on a purely statistical, bottom up methodology. In this paper we advocate the use of a knowledge based approach to improving ASR in domains such as mobile robotics. A simple implementation is presented, which uses the visual recognition of objects in a robot's environment to increase the probability that words and sentences related to these objects will be recognized.
Type of material: Conference Publication
Publisher: IJCAI Workshop
Keywords: Automatic Speech Recognition (ASR);Mobile robotics;Speech priming model
Language: en
Status of Item: Peer reviewed
Is part of: Proceedings of 18th International Joint Conference on Artificial Intelligence (IJCAI-03), 9th-15th August, Acapulco, Mexico
Conference Details: The 18th International Joint Conference on Artificial Intelligence (IJCAI-03), Acapulco, Mexico, 9-15 August 2003
Appears in Collections:Computer Science Research Collection

Show full item record

Google ScholarTM

Check


This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.