Improving multimodal integation:|bExploring a scenario domain approach

Exploring a scenario"domain approach to improve multimodal integration involved speech and sketch in determining the scenario categories of point"to"point, description and query-based. Sketch or speech alone cannot give a clear explanation about a location especially if it is need to...

Full description

Saved in:
Bibliographic Details
Main Author: Lee, Cynthia Poh Choo
Format: Thesis
Language:English
Published: 2012
Subjects:
Online Access:http://ir.unimas.my/id/eprint/10802/3/Improving%20Multimodal%20Integration%20%3B%20Exploring%20A%20Scenario%20Domain%20Approach%20%28fulltext%29.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-unimas-ir.10802
record_format uketd_dc
spelling my-unimas-ir.108022023-03-06T02:39:51Z Improving multimodal integation:|bExploring a scenario domain approach 2012 Lee, Cynthia Poh Choo NX Arts in general Exploring a scenario"domain approach to improve multimodal integration involved speech and sketch in determining the scenario categories of point"to"point, description and query-based. Sketch or speech alone cannot give a clear explanation about a location especially if it is need to go from one place to the others. Objective of this research is to determine the accuracy of predicting different scenario categories based on speech, sketch as well as both speech and sketc~ When both speech and sketch results are combined, the accuracy of prediction is higher compared to solely using speech or sketch only. Overall, the result of the prediction accuracy shows that point-to"point and description scenario categories seem to give a better result compare to query-based scenario category Universiti Malaysia Sarawak, (UNIMAS) 2012 Thesis http://ir.unimas.my/id/eprint/10802/ http://ir.unimas.my/id/eprint/10802/3/Improving%20Multimodal%20Integration%20%3B%20Exploring%20A%20Scenario%20Domain%20Approach%20%28fulltext%29.pdf text en validuser masters Universiti Malaysia Sarawak, (UNIMAS) Faculty of Computer Science and Information Technology.
institution Universiti Malaysia Sarawak
collection UNIMAS Institutional Repository
language English
topic NX Arts in general
spellingShingle NX Arts in general
Lee, Cynthia Poh Choo
Improving multimodal integation:|bExploring a scenario domain approach
description Exploring a scenario"domain approach to improve multimodal integration involved speech and sketch in determining the scenario categories of point"to"point, description and query-based. Sketch or speech alone cannot give a clear explanation about a location especially if it is need to go from one place to the others. Objective of this research is to determine the accuracy of predicting different scenario categories based on speech, sketch as well as both speech and sketc~ When both speech and sketch results are combined, the accuracy of prediction is higher compared to solely using speech or sketch only. Overall, the result of the prediction accuracy shows that point-to"point and description scenario categories seem to give a better result compare to query-based scenario category
format Thesis
qualification_level Master's degree
author Lee, Cynthia Poh Choo
author_facet Lee, Cynthia Poh Choo
author_sort Lee, Cynthia Poh Choo
title Improving multimodal integation:|bExploring a scenario domain approach
title_short Improving multimodal integation:|bExploring a scenario domain approach
title_full Improving multimodal integation:|bExploring a scenario domain approach
title_fullStr Improving multimodal integation:|bExploring a scenario domain approach
title_full_unstemmed Improving multimodal integation:|bExploring a scenario domain approach
title_sort improving multimodal integation:|bexploring a scenario domain approach
granting_institution Universiti Malaysia Sarawak, (UNIMAS)
granting_department Faculty of Computer Science and Information Technology.
publishDate 2012
url http://ir.unimas.my/id/eprint/10802/3/Improving%20Multimodal%20Integration%20%3B%20Exploring%20A%20Scenario%20Domain%20Approach%20%28fulltext%29.pdf
_version_ 1783728075695980544