| |
milestones in text-to-speech conversion (Klatt 1987) | d24 - d25 - d26 - d27 - d28 - d29 - d30 - d31 - d32 - d33 - d34 - d35 - d36 - | |
Part D: Full text-to-speech conversion | ||
 listen to demonstration  technical details  text/transcript  | ||
 |
d24 The first full text-to-speech system, done in Japan by Noriko Umeda et al., 1968. | |
|
d25 The first Bell Laboratories text-to-speech system, by Cecil Coker, Noriko Umeda, and Cathrine Browman, 1973. | |
|
d26 The Haskins Laboratories text-to-speech system, 1973. | |
|
d27 The Kurzweil reading machine for the blind, Raymond Kurzweil, 1976. | |
|
d28 The inexpensive Votrax Type-'n'-Talk system, by Richard Gagnon, 1978. | |
|
d29 The Echo low-cost diphone concatenation system, about 1982. | |
|
d30 The M.I.T. MITalk system, by Jonathan Allen, Sheri Hunnicutt, and Dennis Klatt, 1979. | |
|
d31 The multi-language Infovox system, by Rolf Carlson, Björn Granström, and Sheri Hunnicutt, 1982. | |
|
d32 The Speech Plus Inc. Prose-2000 commercial system, 1982. | |
|
d33 The Klattalk system, by Dennis Klatt of M.I.T., which formed the basis for Digital Equipment Corporation's DECtalk commercial system, 1983. | |
|
d34 The AT&T Bell Laboratories text-to-speech system, 1985. | |
|
d35 Several of the DECtalk voices. | |
|
d36 DECtalk speaking at about 300 words/minute. | |
 | ||