Speech Recognition and Lip Synching
By Mohammed Akel
During my research into the ways in which VR can be used to improve alternative and augmentative communication, I was hoping to explore the possibility of generating speech in virtual environments in order to explore the full potential of VR applications in the field of AAC. The .apk file below contains a character with noticeable facial features. For now, the application will verbally repeat whatever speech it receives. The idea is to explore whether lip-synching is more efficient in VR. A really interesting improvement to such an application would be the addition of text-to-speech features. Due to time constraints, I was not able to conduct such an evaluation exercise.
The .apk file can be found here; Refer to the wiki for more information on how to sideload the file to your headset.