speech synthesis

Speech synthesis is the computer-generated simulation of human speech. It is used to translate written information into aural information where it is more convenient, especially for mobile applications such as voice-enabled e-mail and unified messaging . It is also used to assist the vision-impaired so that, for example, the contents of a display screen can be automatically read aloud to a blind user. Speech synthesis is the counterpart of speech or voice recognition . The earliest speech synthesis effort was in 1779 when Russian Professor Christian Kratzenstein created an apparatus based on the human vocal tract to demonstrate the physiological differences involved in the production of five long vowel sounds. The first fully functional voice synthesizer, Homer Dudley's VODER (Voice Operating Demonstrator), was shown at the 1939 World's Fair. The VODER was based on Bell Laboratories' vocoder (voice coder) research of the mid-thirties.

Speech prosthesis is computer-generated speech for people with physical disabilities that make it difficult to speak intelligibly. Much of the research in this area integrates text and speech generation both, since the disabilities that create problems with speech frequently make text entry difficult as well. Given the speed and fluidity of human conversation, the challenge of speech prosthesis is to circumvent these difficulties. The main research goal is to create a prosthetic system that will as closely as possible resemble natural speech, with the least required input from the user. Speech prosthesis systems also make it possible for visually-impaired people to use computers.

Multimodal speech synthesis (sometimes referred to as audio-visual speech synthesis) incorporates an animated face synchronized to complement the synthesized speech. The same difficulties underlying an individual's speech impairment often hinder their ability to communicate through facial expressions. Although synthesized speech is increasingly life-like, it may be quite some time before it approaches the capacity for nuances of natural speech. Multimodal systems incorporate a means of adding non-verbal cues to speech (such as head-shaking, smiling, and winking, for example) to make the user's meaning as clear as possible.

More from Related TechTarget Sites