Paper Title
Voice Transformation Techniques

Voice transformation is one of the applications in speech processing which involves modification of speech signal of source speaker to a target speaker. This paper describes new techniques for generating speaker-dependent pitch contours for particular short sentences. Here speech signal of source speaker is Neutral speech and speech signal of target speaker is Angry speech. We have proposed 2 transformation algorithms for emotion conversion. The proposed algorithms starts with pitch tracking for both reference and target speakers. And then modifies reference speaker’s pitch according to target speaker’s pitch by using different techniques proposed in the algorithms. In both the algorithms, statistics are used to form a mapping function from a reference speaker’s pitch frequency to the appropriate value for a second speaker.