So.. its been a long while since i’ve had a project to keep me busy and learn a lot with and also to keep me posting. I’m hoping this will be an ongoing one.
I’m starting my own personal digital assistant project. Now… a lot of people have done similar projects. I’m hoping that mine is somewhat unique in that I don’t plan on automating everything in my house although there may be some of that later in the project.
My primary goal is to slowly integrate different functionality into the system so that I can talk naturally with (pablos) Brain and have it respond semi intelligently. Not having to remember “commands” said in specific sequence like most current uses of voice recognition. Ultimately i’d love for it to work for anyone in my house or via mobile phone through a simple audio recording app that submits the audio requests to the server. Very similar to Apples Siri, but hopefully with more over all functionality. But, matching Siri in capabilities is definitely something I hope to reach sooner than later.
I’ve already accomplished several tests utilizing Python and Windows 7’s built in Speech Recognition and Text To Speech capabilities. I’ll post on that separately in more detail soon. And have also done a lot of research into various solutions for text to speech and different output voices. I will hopefully finish documenting a plan and post that on here soon. I don’t plan to be on any schedule and don’t plan to sell this ever… but I do plan on sharing what I find in this journey. I hope that it is interesting for others besides just being a documenting process for myself.