Voice Transformation and Detection

Voice transformation is altering one person’s voice into another person’s voice in such a way that the source speaker’s words sound like they are the target speaker’s. In Phase I, we have studied various algorithms for voice transformation. The project has come to grips with the feasible methods for glottal source and vocal tract conversion algorithms; thus laying a good foundation upon which this Phase II project can be successfully implemented. The objective of this Phase II proposal is threefold; to develop state-of-the-art voice transformation technologies, to develop a voice transformation platform (VTP) and to develop a prototype of a real-time voice transformation system (RVTS). Firstly, we will develop various state-of-the-art algorithms, which we identified as candidate technologies for Phase II. The VTP is a software application where users can perform the entire process of voice transformation, including data collection from speakers, automatic training of the conversion functions for vocal tract and glottal source, and eventually real-time voice transformation. The RVTS is a hardware system that transforms an input voice to a pre-determined target speaker’s voice. We are confident that the software and hardware developed at the end of Phase II will be important elements in future voice transformation systems.