Lessac Technologies Demonstrates Expressive Text-to-Speech

A human voice provides meaning and identity simultaneously. For many years, speech technology companies have sought to have a computer synthesize speech that matches the expressive meaning and individualized identity capabilities of a human voice -- they have not yet succeeded. Expressive human speech is prosodic -- it is musical, with melodies and rhythms that clarify words and phrases, as well as create the auditory context to enhance a listener's comprehension.

Lessac has developed a new automated method for producing near human quality expressive speech from plain text; the synthesized speech produced by Lessac's prototype demonstrator sounds quite similar to speech from a skilled newscaster.

The foundation for Lessac's unique technology is the 50 years of voice research by renowned speech professor and practitioner Arthur Lessac. Since the early 1930s, Arthur Lessac has been investigating how the human body and voice function naturally and instinctively. Arthur Lessac has established the Lessac Training and Research Institute to extend his legacy. (www.lessacinstitute.com)

 Please click here to play a synthesized version of this page.

Try a demo of Lessac expressive voice synthesis with your text.