by justingibbs on August 7, 2008
YouTube introduces speech-to-text, Adobe planning to add speech-to-text to Flash later this year. Besides the feature being exceptionally cool, it also gives me hope that intelligent virtual characters will have similar functionality. Natural language processing technology works by first normalizing the input - splitting up sentences, converting apostrophes, and more so that the program can begin to interpret what the user is saying. If the user is communicating through voice it must first be converted to text, hence speech-to-text.
We’ve had text-to-speech for years, albeit the voice quality has been lacking it is getting better. We’ve also had speech-to-text for a few years, but it’s great to see YouTube and others moving into the space. Just think if we could get virtual Mr. T here to not only chat with you through text chat, but also through voice. Making him sound just like the real Mr. T might prove more of a problem.
The main question for integrating it into TapBot and using it to create intelligent virtual characters is just how processor intensive is it? Second Life already bogs down computers. But having others implementing the technology bode well for improvements. Now if we can only get an open source solution.
by justingibbs on August 6, 2008
TapBot’s Big Hairy Audacious Goal (”BHAG”) - Turn virtual worlds into a medium for immersive story where players interact in real time with computer controlled characters and environments. Basically modify AI and virtual world technology so that artists can use it to create immersive story.
The first step will be to build an open source immersive story engine. My difficulty with this is that I’m not a developer. I’m just a project manager turned social media strategist. But I’ve spent years in a failed attempt to become a screenwriter and know more than a thing or two about narrative story. So I’ll do what I do as a project manager - start building support for the project and fleshing out scope/requirements. Of course things work a little differently with open source development. Open source projects start with code. You can’t even get a project listed on freshmeat unless you have some code to start with. But I’m going to go against the grain and starting the process anyhow. Hopefully as others see me doing this in the open it will attract others to the project and if we’re lucky - pull in some developers.
So the goal - well I sort of stole that from Mozilla Labs Concept Series as it’s similar to what I’m attempting to do.
Goal of the Blog
The goal of the TapBot blog is to bring more people to the table and provoke thought, facilitate discussion, and launch an open source project to build an immersive story engine.
A Committee of One
Of course today there’s just me. I’m a committee of one. But that is how many projects start and as Hal Fulton points out, it might have been beneficial for David Heinemeier Hansson developing Ruby on Rails.
Another thing Hansson did right was to do it himself. Ruby on Rails, like Ruby itself, started as the unified concept of one single person. Certainly, Rails is open source, with many developers helping to expand it, and that is part of its strength. Hansson probably had extensive advice and assistance even in the early stages. But it started as the dream of one person, the vision of a single individual. I don’t know what others may call this, but I call it the “Committee of One” principle. (I wish I had a cool acronym for this concept.)
Join the Discussion
I’ll continue to plug away on this but would love if others joined me. So please subscribe and leave a comment. If you blog about something here please link back through trackback or pingback. I’m looking to start a forum, but that’s a bit premature at the moment.
For more information about me, my thoughts on the metaverse and immersive story you can always check out my personal blog. You can also contact me through that blog.
