Date of Award

2006

Publication Type

Master Thesis

Degree Name

M.Sc.

Department

Computer Science

Keywords

Computer Science.

Rights

info:eu-repo/semantics/openAccess

Abstract

A SpeechWeb is a collection of hyperlinked speech applications that are distributed over the Internet. Users access the speech applications through remote browsers, which accept human-voice-input and return synthesized-voice-output. In previous research, a new architecture (LRRP) has been proposed, which is ideally suited for building a Public-Domain SpeechWeb. However, a non-proprietary speech browser is needed for this architecture. In this thesis, we have solved several limitations of X+V, a programming language for developing Multimodal applications, and we have used X+V to build a viable Public-Domain SpeechWeb browser. Our browser has the following properties: real-time human-machine speech interaction; ease of installation and use; acceptable speech-recognition accuracy in a suitable environment; no cost, non-proprietary, ease of distribution; use of common communication protocol---CGI; ease of creation of speech applications; possibility to deploy on mobile devices.Dept. of Computer Science. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis2006 .M31. Source: Masters Abstracts International, Volume: 45-01, page: 0360. Thesis (M.Sc.)--University of Windsor (Canada), 2006.

Share

COinS