The rise of smart mobile applications like Apple's Siri and Google Now has impressively demonstrated how viable speech recognition can be to accomplish otherwise cumbersome tasks quickly and easily. However, speech input is still largely a gimmick in current systems and the uptake on traditional desktops is all but non-existent. The KDE Accessibility (and now the newly founded KDE Speech team) has been working hard on bringing open source speech recognition to the KDE desktop. Want to lead the way in bringing speech-enabled applications to your favorite desktop Attend this talk to find out how you can integrate speech recognition in your very own projects and put Siri to shame.
At least perfunctory knowledge about software development. Best suited for current or prospective developers of KDE applications.
Talk Difficulty Level:
Peter Grasch is the maintainer and main developer of the KDE speech recognition software Simon. Currently, he is finishing up his master's degree in computer science at the Graz University of Technology.LinkedIn: http://www.linkedin.com/profile/view?id=150418403