This is Chippu, a robot that [Achu] has been working on for some time. His most recent addition was to give the robot the ability to respond to voice commands. This is accomplished using a variation of the open source Continuous Speech Recognition package called Julius.
The package depends on two main parts, a set of acoustic models which let it match incoming sounds and a reference library of grammar which is built from those sounds. [Achu] published another post which goes into detail about using Julius on a Linux box. It seems like this is possible with less robust hardware (ie: on an embedded system) if you narrow down the number of acoustic and grammer models that need to be matched.
For now, Chippu is getting commands from a computer that runs the CSR. But this was only used as a proof-of-concept and [Achu] plans to transition the bot over to smaller hardware like the BeagleBoard.
Check out the demonstration of Chippu responding to voice commands in the video after the break.
[youtube=http://www.youtube.com/watch?v=WHMeLI0H9f4&w=470]
Incredible job of integrating COTS stuff into a functioning ‘bot. Good Work. This also can be so much more. I’ve a grandson recovering from a brain tumor. They were discussing service animals for him.
But a service animal cannot parse speech into a defined action of “controlling something” directly. This hack *DOES* just that parse&control in it’s own fashion.
This is a project that Hackerdom can show our chops as hero’s with. Who’s going to be the first to use this as an assist tech tool? Even in it’s present incarnation I can see it being almost “good enough” to fetch some dropped objects that frustrate the bed or chair bound. This sort of hack makes me PROUD of us all! As we’re making science fiction into reality and potentially life so much easier for folks who need all the assist we can give them.
Oh- the “Social Hack” here is a shout out to someone @ Arch Reactor who reminds us that we can use our powers for Good or Awesome
Thank you sir for your inspiration… May your grandson recover soon… My prayers are there for him….. and i am gonna really do something for the folks who need all the assistance..
Here is a similiar project using the voce java library for recognition, and freetts for speech.
http://youtu.be/6J6bjd_7hgQ
The Voice stuff is the most interesting. Linux needs more Voice input projects like this.
Open source Customer Support Representative(CSR)?
That’s kind of wierd.
He reminds me of the “stabby” robot Roberto from Futurama. Be careful or he’ll cut you!
If someone took the time to shoehorn something like the Julius with a minimal Linux distro into some sort of small cheap platform like that picture frame that was posted on Tuesday (http://hackaday.com/2012/01/10/this-digital-picture-frame-runs-linux-better-than-you-might-think/), I bet that could be a really cheap, simple way to add voice control to all sorts of robotics or automation projects…
excellent….