Voice Transformation

Abstract

Voice transformation voicetransformation refers to the various modifications one may apply to the sound produced by a person, speaking or singing. In this chapter we give a description of various ways in which one can modify a voice and provide details on how to implement these modifications using a simple, but quite efficient, parametric model based on a harmonic representation of speech. By discussing the quality issues of current voice transformation algorithms in conjunction with the properties of speech production and perception systems we try to pave the way for more-natural voice transformation algorithms in the future.