The Takanishi Laboratory, at Waseda University, Japan, is home for many robotic projects, including a flutist I wrote about a while ago. 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 are similar to human ones. The next version, the WT-5, will have even more sophisticated vocal cords. Read more.
Here is the WT-4 "saying" an "A" (Credit and copyright: Takanishi Laboratory). This image has been extracted from one of the four QuickTime movies available on the WT-4 homepage mentioned above.
Here are more details about the WT-4.
We developed a new anthropomorphic talking robot WT-4 (Waseda Talker No.4) that improved on WT-3. WT-4 had a human-like body to make the communication with a human more easily, and consisted of 1-DOF lungs, 4-DOF vocal cords and articulators (the 7-DOF tongue, 5-DOF lips, 1-DOF teeth, nasal cavity and 1-DOF soft palate), and could reproduce human-like articulatory motion; the total DOF was 19. We improved the connection mechanism between the vocal cords and the vocal tract and developed the new vocal cords. As a result, WT-4 could produce Japanese vowels that were more similar to human vowels than the previous robots and could produce stops, fricatives and nasal sounds of 50 Japanese sounds for human-like speech production.
For more information, two papers about the Wased Talker will be presented at the 149th Meeting of the Acoustical Society of America, which will be held on May 16-20, 2005, in Vancouver, Canada.
One thing is plain for all men of common sense and common conscience, that here, here in America, is the home of man. After all the deductions which are to be made of for our pitiful politics, which stake every gravest national question on the silly die, whether James or whether Jonathan shall sit in the chair and hold the purse; after all the deduction is made for our frivolities and insanities, there still remains an organic simplicity and liberty, which, when it loses its balance, redresses itself presently, which offers opportunity to the human mind not known in any other region.
—Ralph Waldo Emerson (1803–1882)
The first one, "Development of an anthropomorphic talking robot and the mimicking speech control," will be about the WT-4 and show "that this mimicking speech control is effective in producing fluent continuous speech by the talking robot." Here is a link to the abstract.
The second one, "Mechanical vocal cord model mimicking human biological structure," is about the next version of the Talker, the WT-5. And here are a link to the abstract and a selected quote.
Unlike a musical reed which has been used in conventional mechanical speech synthesizer, the vocal cord model is formed to mimic the human's vocal cord in the shape and the biological structure. It is made of a thermoplastic rubber, Septonh (Kuraray Co. Ltd.) of which the elasticity like a human's, and has 3-DOF mechanisms which is similar to the human structure. 1-DOF link mechanism could change the pitch by stretching the length of the vocal cords. The 2-DOF arm mechanism is used to mimic the abduction and adduction of a human arytenoid cartilage.
If you happen to be around Vancouver in May, these two presentations will be given on May 19 in the morning.
Sources: Takanishi Laboratory, Waseda University, Japan; and various websites
The beginning of human knowledge is through the senses, and the fiction writer begins where human perception begins. He appeals through the senses, and you cannot appeal to the senses with abstractions.
—Flannery O’Connor (1925–1964)
Related stories can be found in the following categories.
Miscellaneous
Robotics
Science.