Speech input software is assistive technology that allows users to interact with devices using voice commands. It can also allow spoken words to be transcribed into text.
Bell Laboratories developed the first speech recognition system, "Audrey," in 1950.
"Audrey" took up a whole room and could only identify the numbers 1-9, but did so with 90% accuracy.
Debuted at the World's Fair in 1962, IBM's Shoebox could recognize 16 different words.
The Department of Defense, in the early 1970s, recognized the value of speech recognition and invested 5 years into DARPA’s Speech Understanding Research program.
In 1978, Speak & Spell was introduced, a children's toy designed to help them spell out words.
All of this paved the way for common devices such as Siri (2011) and Alexa (2014).
Comments