What is a Speech Synthesizer?

Article Details
  • Written By: Malcolm Tatum
  • Edited By: Bronwyn Harris
  • Last Modified Date: 19 October 2019
  • Copyright Protected:
    Conjecture Corporation
  • Print this Article
Free Widgets for your Site/Blog
In 2008, Mike Merrill became the first publicly traded person, allowing shareholders to control his life decisions.  more...

October 23 ,  1983 :  Suicide bombers killed nearly 300 US and French military troops in Beirut.  more...

The speech synthesizer is device that is used to translate text characters into sounds that approximate the sound of human speech. Depending on the level of sophistication of the individual device, the sounds produced may be somewhat stilted and artificial sounding, or sound very much like the voice of a real person. The concept of speech synthesis has been around for centuries, but only in recent decades has the process become available to the general public.

There are examples of attempts to artificially produce human speech patterns that go back to the 11th century. The earliest attempts often used materials to replicate human vocal cords and apply various types of stimulation in order to produce sounds. Over time, designs made it possible to produce sounds that mimicked the pronunciation of vowels. By the latter part of the 18th century, a few designs were also able to produce sounds that closely resembled consonants.

The real progress with the modern speech synthesizer began in the 1930’s. Bell Laboratories produced a synthesizer that was dubbed the vocoder. Data was entered with the use of a keyboard, analyzed by the system, and the appropriate sounds emitted to form words. While the intonation and inflection of the words were somewhat primitive, the device did produce clearly intelligible words. A refined version of this device, the voder, was introduced to the public at the 1939 World’s Fair.


By the 1950’s, work on a speech synthesizer that would use visual images as well as entered text produced partially successful results. At the same time, advances in technology began to refine the sound quality. By the time that automated voice communications became more prevalent in the 1970’s, there were several speech synthesizers that were capable of producing sounds that were very close to human speech patterns. In a short time, the devices were being used to produce such products as pre-recorded messages on answering machines and reading products for persons who were visually impaired.

The advent of the personal computer also opened the door to further refinements for the speech synthesizer. By including the device on a home computer system, persons with reading disabilities or limited vision are able to enjoy using a variety of computer programs. Today, the voice quality on most models of the speech synthesizer is far removed from the robotic sounds produced by devices created in the early 20th century. Many versions today are capable of producing voice patterns that are almost indistinguishable from human speech.


You might also Like


Discuss this Article

Post 1

Wow, I had no idea how far back in history the idea of speech synthesis went. Speech synthesis is something that’s always interested me but I’ve never really bothered to read up about it. I mainly think about it in terms of Stephen Hawking, but the text to speech software I’ve used sounds nothing like he does; I wonder if he made a conscious decision to stick with the hardware and software he’s got? It definitely has a kind of old school charm compared to today’s text to speech software.

Post your comments

Post Anonymously


forgot password?