Speech Recognition in Grasshopper

A one hour test with speech recognition in Grasshopper. It's the first time I've ever used the Windows in-build recognition engine, or indeed invoked it through code. I'd say definitely mixed results.

18 members like this

Get Embed Code

Tags:

Comment

You need to be a member of Grasshopper to add comments!

Comment by David Rutten on June 27, 2012 at 12:57pm: Andy, it's not a work in progress, it's just a script component that uses System.Speech.Recognition Just some dicking around really.

Comment by Andy Payne on June 27, 2012 at 11:41am: Very nice. I had thought about trying to implement some sort of speech recognition component for the Firefly Kinect components... but I always felt that using the Windows built-in engine would be better, as it would be available to a much wider audience. I'm curious how you set it up. Would you mind sharing your solution (even though I know it's still a work in progress)? It would just be helpful to see how you set it up... also, it would allow others to test it using their own voices and see how closely the results matched your own. Thoughts?

Comment by David Rutten on June 27, 2012 at 10:04am: Benjamin, yes, it seems possible to supply a custom grammar for speech recognition, and this grammar could restrict itself to just component names and keywords. Haven't tested yet, only gave myself an hour for this... clusters were calling :)

Comment by Arie-Willem de Jongh on June 27, 2012 at 8:32am: Some day just by talking we're constructing the 3D model:

"column steel @ 50,45,0', 'beam wood @ 50,30,0' etc.

Really nice David!