Biographical / Historical
The Smithsonian Speech Synthesis History Project, conducted by H. David Maxey from 1986 through 2002, created a collection of archival materials including sound recordings documenting the history and development of speech synthesis technology. Maxey collaborated with Dr. Bernard Finn of the National Museum of American History's Division of Information, Technology, and Society. Elliot Sivowitch and Harold Wallace of the same division served as Smithsonian liaisons with the project.
"Speech synthesis technology" refers to the results of a long, evolutionary process in which researchers learned to create artificial sounds that people would interpret as speech. As early as the eighteenth century scientists were inventing mechanical machines to create sounds similar to human speech. Later electronics led to additional developments, The Voder was one of the earliest examples which was demonstrated to wide acclaim at the 1939 New York World's Fair. However, it was the widespread use of computers that led to the greatest progress in the field of speech synthesis.
Speech synthesis is the process by which a computer speaks. By contrast, speech recognition is when a computer can interpret spoken language. The application of both of these capabilities has been important for creating assistive computer technology for the visually impaired (speech recognition) and for individuals unable to speak (speech synthesis).
Among the leading researchers and organizations involved with the development of speech synthesis technologies are the Anerican Telephone and Telegraph Company (AT&T), Bell Telephone Laboratories, International Business Machines Corporation (IBM), the Massachusetts Institute of Technology (MIT), Dennis H. Klatt, and Ray Kurzweil.
Today speech synthesis is a common feature of daily life from the cultured voice on the GPS saying exactly which road to take to making a train reservation on the telephone. However, many speech synthesis developers continue to explore and design methods to make the speech sound less mechanical, with the ultimate challenge being natural sounding speech that shows emotion.
Dave Maxey's dedication to the project, with support from members of the staff of the National Museum of American History, has ensured the preservation of materials documenting the early history of electronic and computer engineered synthetic speech.