Speech recognition and synthesis

  • Authors:
  • Jonathan Allen

  • Affiliations:
  • -

  • Venue:
  • Encyclopedia of Computer Science
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

The use of computers could be greatly expanded if human speech could be reliably used as an input-output medium. Such capability would allow humans to listen to synthetic speech output from a computer rather than read a display. Indeed, commercially acceptable synthetic speech can now be produced as output from a computer, even for unrestricted vocabulary and syntax. The ability of computers to recognize human speech would permit input to the computer without the use of a keyboard. Although commercial units of limited capability are available, speech recognition is a far more difficult problem than speech synthesis.