The Sound Control project is aimed at people who have difficulties using the PC, but for whom traditional word-based voice recognition falls short, for example because they cannot pronounce words clearly and/or systematically enough for a traditional word-based voice recognition system to understand them. Until now, there has been little focus on these users, both nationally and internationally.
The Sound Control project will consider functional requirements and solutions for PC-interaction using spoken sounds. The project will thus investigate the possibilities of a sound-based voice management system for PCs.
MediaLT has led the development of a Norwegian command-based voice recognition PC control system in Windows through the projects SMUDI (prosjektnr.183215/S10) supported by NFR (Norwegian Research Council), and Vomote (prosjektnr.145589) supported by Innovation Norway/Tillvekstvärket. We now want to further exploit this knowledge of voice technology for the benefit of the user group specified above, by looking at the opportunities for developing a sound-based voice management system for PCs.
Tips noen om siden