Improving Speech Recognition on a Mobile Robot Platform through the use of Top-Down Visual Queues
Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence. Pages 1557-1558.
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.
@inproceedings{ijcai2003p271,
title = {Improving Speech Recognition on a Mobile Robot Platform through the use of Top-Down Visual Queues},
author = {Ross, Robert J. and O'Donoghue, R. P. S. and O'Hare, Gregory M. P.},
booktitle = {Proceedings of the Eighteenth International Joint Conference on
Artificial Intelligence, {IJCAI-03}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Georg Gottlob},
pages = {1557--1558},
year = {2003},
url = {https://ijcai.org/proceedings/2003/271},
}
TY - CPAPER TI - Improving Speech Recognition on a Mobile Robot Platform through the use of Top-Down Visual Queues AU - Ross, Robert J. AU - O'Donoghue, R. P. S. AU - O'Hare, Gregory M. P. T2 - Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence, IJCAI-03 PB - International Joint Conferences on Artificial Intelligence PY - 2003 SP - 1557 EP - 1558 UR - https://ijcai.org/proceedings/2003/271 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
