I'd like to create a computer program based on speech recognition.
The user should be able to select a specific scenario from a list of available options, and then a video will start. The video will be a pre-recorded snippet of a person talking, and the user can 'speak' to the person in the video, the program would recognise key words/phrases and then play an appropriate video in response.
At the end of the scenario the user will be given a score based on how many of that course's videos were brought up.
Ideally i'd also like for the system to allow for me to upload the 'courses' myself, so I can create my own courses comprised of video --> voice command --> video --/etc/--> grading.
I would also like for the videos to be optionally viewed with VR headsets, such as Oculus.
I'm an independent person, and would like to discuss the feasibility and costing of the project.