Artificial Vocal Tract for Robots

Posted 4 May 2002 at 14:21 UTC by steve Share This

Hideyuki Sawada of Kagawa University in Japan is developing an artificial vocal tract for use in humanoid robots. This is not an electronic voice synthesizer but a mechanical assembly that simulates the human vocal tract by pumping air through vocal chords, a windpipe, and lips. The system is controlled by a neural network. A NewScientist.com article provides a nice summary of the project.

Heimleich, posted 4 May 2002 at 22:22 UTC by The Swirling Brain » (Master)

For crying out loud, wouldn't it be easier to get a cheapo 50 cent speaker and do the sound stuff virtually with software? When the difference is a 50 cent device or a 50 dollars device with comparible output, I'll go with the 50 cent device. It's like the difference between an old $100k pipe organ and a $2k Clavinova, why have the expensive one when you can have it all with the inexpensive one. But of course the expensive one looks nice and all. Really, though, I've thought it would be neat to do this too.

See more of the latest robot news!

Recent blogs

30 Sep 2017 evilrobots (Observer)
10 Jun 2017 wedesoft (Master)
9 Jun 2017 mwaibel (Master)
25 May 2017 AI4U (Observer)
25 Feb 2017 steve (Master)
16 Aug 2016 Flanneltron (Journeyer)
27 Jun 2016 Petar.Kormushev (Master)
2 May 2016 motters (Master)
10 Sep 2015 svo (Master)
14 Nov 2014 Sergey Popov (Apprentice)
Share this page