Early Computer Speech Synthesis

The first computer-based speech synthesis systems were created in the late 1950s, and the first complete text-to-speech system was completed in 1968. In 1961, physicist John Larry Kelly, Jr and colleague Louis Gerstman used an IBM 704 computer to synthesize speech, an event among the most prominent in the history of Bell Labs. Kelly's voice recorder synthesizer (vocoder) recreated the song "Daisy Bell", with musical accompaniment from Max Mathews. Coincidentally, Arthur C. Clarke was visiting his friend and colleague John Pierce at the Bell Labs Murray Hill facility. Clarke was so impressed by the demonstration that he used it in the climactic scene of his screenplay for his novel 2001: A Space Odyssey, where the HAL 9000 computer sings the same song as it is being put to sleep by astronaut Dave Bowman. Despite the success of purely electronic speech synthesis, research is still being conducted into mechanical speech synthesizers.

• Category

  Science & Technology

[sinborn41214]

hey the computer singing "daisy daisy" at 0:48 sounds alot like most pop singers nowadays

[ichbinfantomashehehe]

00:39 very Realistic Voice

[TheZombie153]

a sea of gerbils :]

[mybluebelly]

I love this video !!!!!!!!!!!!!!!!!.....!

[supahspyrosonicfan98]

The voices on my Macintosh sound more human then this. It's amazing how far synthesized voices have come a long way. Imagine what voices like that could sound like in 20 years or less.

[Ngivesmenightmares]

I just found it funny how difficult english is to speak but easy to sing for vocalsynth programs, as other languages are more simple for them because of how their structured like singing so now it makes allot more sense to me

[Hans Kamp]

Singing is easy because you program the pitch and the length of each note. In case of talking this is way more difficult.

[Hans Kamp]

I agree. Therefore I think, singing is easier for a computer than talking.

About singing, a while ago I had a polyphonic singing sequencer. You program the notes as in a normal sequencer but instead of instruments you choose male and female voices and the speech is given under the right notes. This makes the program pretty user friendly. After clicking on play you will here a singer (when you use one note at a time) or a choir (in case of multiple notes simultaneously).

[DJP0N3Brantonisme]

Wasn't this the same program that was used for the computer in Gumby: The Movie (1995)?

[DeeperDarkest]

It's all the cat?

[Jalen Rantschler]

I wonder if he could sing baby? Hmmmmm.....

[Jalen Rantschler]

I can't tell what he (yes I believe computers are male or female too) is saying