Robotics Reference
In-Depth Information
Mechanical Speech Synthesis
The ability to communicate our thoughts, feelings and desires effectively
to other human beings through language is one of the characteristics of
being human. Any self-respecting super-robot of the future, one that
can communicate with us in our own way, must therefore possess the
facility of speech (as well as the ability to understand what is said to it).
The history of “talking machines” dates back to the ancient Greeks and
Egyptians and their talking oracles. In order to impress citizens with
devices that appeared to be able to communicate through some divine
means, huge idols such as the “speaking head” of Orpheus at Lesbos had
long talking tubes connected to them, giving the impression that the
head was talking.
The science of speech synthesis, as it is nowadays called, has its foun-
dations in the eighteenth century, with the first attempt to simulate the
human speech mechanism using a bellows and vibrating reeds. A few
such devices were developed around that time, the earliest of which ap-
pears to have been by none other than Baron Wolfgang von Kempelen,
he of the Chess Automaton. In 1771 Erasmus Darwin, the grandfa-
ther of Charles Darwin, announced that he had “contrived a wooden
mouth with lips of soft leather, and with a valve over the back part of
it for nostrils.” Darwin's contraption had a larynx made of “a silk rib-
bon...stretched between two bits of smooth wood a little hollowed.”
It could say “mama”, “papa”, “map” and “pam” in “a most plaintive
tone”. Other early devices included one fabricated by Christian Kratzen-
stein, who was a professor of mechanics in St. Petersburg and profes-
sor of physics and medicine in Copenhagen, and one by Abbe Mical in
France.
Von Kempelen's Talking Machine
Von Kempelen purportedly began work on his speech device in 1769
but it was not completed until 1791. His work started two years ahead
of Darwin's announcement and ahead of the completion and demonstra-
tion of Mical's machine in 1778 and Kratzenstein's in 1779, the latter
winning the annual prize of the Imperial Academy of St. Petersburg. Al-
though von Kempelen's machine received considerable publicity, it was
not taken as seriously as it should have been, possibly because of doubts
and rumours concerning whether or not his Chess player was genuine
science or a fraud. His speaking machine, however, was a completely
