Speech synthesis at Bell Labs dates back to the 1930s and Homer Dudley's Voder, which was exhibited and publicly demonstrated at the 1939 World's Fair. Because understanding all aspects of the conversion of speech to electrical signal was a core interest of the Bell System, speech synthesis research continued at the company in the ensuing decades, entering the computer era in the 1960s, with articulatory speech vocal tract models created by Paul Mermelstein, Cecil Coker, John L. Kelly Jr., and Louis Gerstman, among others. Text-to-speech programs were researched from the 1960s all the way to the present day.
This film specifically documents the output of an early text-to-speech program. Cecil Coker worked on this project, which is an articulatory synthesis program. (This photo shows Coker providing input to the system). Coker most likely first presented this film at a conference, either in Japan or at the 1967 M.I.T. Conference on Speech Communication and Processing, or the 1968 Processed Speech Symposium in Kyoto.
Coker was also one of the scientists at Bell Labs involved with the E.A.T. collaborations with artists program; he added technical expertise to art performances by John Cage and Robert Rauschenberg.
To read and hear more online:
- Bell Laboratories produced two recordings demonstrating synthesized speech. You can hear both of them here: "He Saw the Cat" 45; "Synthesized Speech" flexidisc
- The best resource for the history of speech synthesis resides at the Smithsonian, and is documented extensively online.
- Bell Laboratories made a speech synthesis kit for high school students in 1963.
- AT&T still does research in this area, specifically with the Natural Voices program, which is licensed commercially.
Footage Courtesy of AT&T Archives and History Center, Warren, NJ