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

Files in This Item:
 File SizeFormat
DownloadP181-Ross,O¿Donoghue,O¿Hare-03.pdf12.14 kBAdobe PDF
Title: Improving speech recognition on a mobile robot platform through the use of top-down visual queues
Authors: Ross, RobertO'Donoghue, R. P. S.O'Hare, G. M. P. (Greg M. P.)
Permanent link: http://hdl.handle.net/10197/4530
Date: 9-Aug-2003
Online since: 2013-08-14T12:11:10Z
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 roboticsSpeech priming model
Other versions: http://ijcai.org/Past%20Proceedings/IJCAI-2003/PDF/274.pdf
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
This item is made available under a Creative Commons License: https://creativecommons.org/licenses/by-nc-nd/3.0/ie/
Appears in Collections:Computer Science Research Collection

Show full item record

Page view(s)

1,293
Last Week
3
Last month
11
checked on May 19, 2022

Download(s)

245
checked on May 19, 2022

Google ScholarTM

Check


If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.