All the news that's fit to assimilate
[ Home | Blogs | Events | Robots | Humans | Projects | About | Account ]
Roland Piquepaille writes, "The Takanishi Laboratory, at Waseda University, Japan, is home for many robotic projects, including a flutist robot. Today, let's look at a talking robot, the Waseda Talker No. 4, or WT-4. This anthropomorphic talking robot was built to better understand how the human vocal mechanism creates speech. The WT-4 has 19 degrees of freedom (DOF) for lungs, vocal cords, tongue, lips, teeth, nasal cavity and soft palate. With its vocal cords, it can produce Japanese vowels that sound similar to human ones. The next version, the WT-5, will have even more sophisticated vocal cords." For more on the WT-4 and WT-5 robots see Roland's latest blog entry.
Looks great, and is very much in the tradition of Jacques de Vaucanson. The idea of transmitting the speech movements rather than sounds to save bandwidth on mobile phone networks is quite novel, and would potentially mean that you could speak with someone else's voice (pick your favourite celebrity) in real time.By simulating the voice mechanisms in this way it should also be possible to get a far better understanding of the underlying neural control mechanisms involved in producing speech movements. This is similar in principle to the approach taken by Steve Grand with his Lucy robot.
Become a fan on facebook
Follow us on twitter
Subcribe to our RSS feed