A framework for multi-modal input in a pervasive computing environment

In this thesis, we propose a framework that uses multiple-domains and multi-modal techniques to disambiguate a variety of natural human input modes. This system is based on the input needs of pervasive computing users. The work extends the Galaxy architecture developed by the Spoken Language Systems group at MIT. Just as speech recognition disambiguates an input wave form by using a grammar to find the best matching phrase, we use the same mechanism to disambiguate other input forms, T9 in particular. A skeleton version of the framework was implemented to show this framework is possible and to explore some of the issues that might arise. The system currently works for both T9 and Speech modes. The framework also includes potential for any other type of input for which a recognizer can be built such as graffiti input.

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2002

Author dc:creator

• Agarwal, Shalini, 1979-

Advisor dc:contributor.advisor

• Larry Rudolph.

• Electrical Engineering and Computer Science.

Statement dc:rights

• M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/1721.1/16825

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/16825