SOUND ENVELOPE DECONSTRUCTION TO IDENTIFY WORDS AND SPEAKERS IN CONTINUOUS SPEECH

A speech recognition capability in which speakers of spoken text are identified based on the contour of sound waves representing the spoken text. Variations in the contour of the sound waves are identified, features are assigned to those variations, and parameters of those features are grouped into predefined characteristics. The predefined characteristics are combined into voice characteristic groups. If a prior voice characteristic group is present, the voice characteristic group from the soundlet is compared to existing voice characteristic groups and, if a match is present, the sound construct is assigned to a speaker identified by the existing voice characteristic group.