Paper Info
Title
VTQuest: a voice-based multimodal web-based software system for maps and directions
Abstract
Finding our way out at a large university campus is a problem. We developed VTQuest, http://sunfish.cs.vt.edu/VTQuestV, as a web-based software system to solve this problem for the campus of Virginia Tech (http://www.vt.edu/). VTQuest enables (a) multimodal interaction with voice, mouse, and keyboard, (b) browsing the campus map, (c) locating a building by name, abbreviation, category, or within a distance on the campus map, (d) locating a room on the floor plan of a building, and (e) obtaining walking directions from one building to another. VTQuest provides these capabilities for 103 buildings with floor plans for most of the buildings. VTQuest is engineered based on Java 2 Platform, Enterprise Edition (J2EE) using Scalable Vector Graphics (SVG) and Speech Application Language Tags (SALT). SVG enables zooming into the maps without losing image quality. The voice interface offers a variety of features including an extensive grammar and out-of-turn interaction.
Year
DOI
Venue
2006
10.1145/1185448.1185517
ACM Southeast Regional Conference 2005
Keywords
Field
DocType
voice interface,floor plan,campus map,multimodal interaction,voice-based multimodal web-based software,large university campus,speech application language tags,scalable vector graphics,virginia tech,enterprise edition,out-of-turn interaction,client server,image quality,software systems
Scalable Vector Graphics,Multimodal interaction,Speech Application Language Tags,World Wide Web,Computer science,Floor plan,Software system,Voice user interface,Web application,Multimedia,Java
Conference
ISBN
Citations 
PageRank 
1-59593-315-8
3
0.42
References 
Authors
6
2
Name
Order
Citations
PageRank
Thomas W. Schneider130.42
Osman Balci2872175.02