Do you think...

This is John F. Kennedy?

This is a female?

This is a male?

This is an adult?

This is a child?

You are only partially correct!!

Each of these sentences was produced by combining the speech of two speakers with very different characteristics. Only one of the speakers, from whom less than half of the sounds of each sentence was taken, has the voice characteristics you perceived. The sentences are examples of our hybrid speech synthesis, in which only those select segments required to characterize a speaker are actually taken from that speaker's voice. The remaining segments are either synthesized or taken from the speech of other human speakers.

Our ability to create these illusions results from our team's extensive experience in knowledge-based speech synthesis and related technologies, which enables us to predict for any given language which aspects of a speech signal and which types of signal manipulations will be perceptible to the human ear and which will not. Building on a powerful set of perceptual models, we are currently developing improved methods of speech synthesis and speech encoding, and are planning on extending our novel methods into other areas of speech processing.

Web design consulting provided by www.cayugadigitalimaging.com