Artificial voice system says hello

May 1, 2002 | Source: New Scientist

Hideyuki Sawada of Waseda University in Japan is designing an artificial voice system to make interacting with robots more natural.

The system emulates the human lung, windpipe, vocal cords and throat by using a compressed air tank that forces air into a plastic voice-box chamber, where it makes rubber “vocal cords” vibrate. The sounds generated are then fed to a flexible tube that mimics a human vocal tract. The system cannot yet match the quality of digital voice synthesizers.

MPEG Video of the artificial voice system