Introduction: Speech Synthesis Technology
"Speech synthesis technology" refers to knowledge gained from a long, evolutionary process in which researchers learned to create artificial sounds that people would interpret as speech, perhaps somewhat strange speech, yet understandable. Also as part of that process came a better understanding of how human hearing and comprehension works.
The benefits have been many, including computers that can read books to people, better hearing aids, more simultaneous telephone conversations on the same cable, talking machines for vocally impaired or deaf people and better aids for speech therapy.
By way of contrast, "speech synthesis" is the process by which computers speak to people, whereas "speech recognition" is the complementary process by which computers interpret what people say to them.
Here is an example of synthetic speech, created from a hand-prepared pattern at my IBM laboratory in 1965.
At the time of this writing, my weather radio reports the usual statistics by speech synthesis, leaving special bulletins to the human announcers. When a book I've requested comes in, my local library's computer calls me with a notice in synthetic speech. As computer voices become commonplace, who will believe that the problem was so difficult that it took talented and skilled people over six decades to make computers speak intelligibly? This is part of that story.
H. David Maxey, Compiler and Editor