Improving quality of voice conversion systems

Abstract

New improvement scheme for voice conversion are proposed in this paper. We take Human factor cepstral coefficients (HFCC), a modification of MFCC that uses the known relationship between center frequency and critical bandwidth from human psychoacoustics to decouple filter bandwidth from filter spacing, as the basic feature. We propose U/V (Unvoiced/Voiced) decision rule such that two sets of codebooks are used to capture the difference between unvoiced and voiced segments of the source speaker. Moreover, we apply three schemes to refine the synthesized voice, including pitch refinement, energy equalization, and frame concatenation. The acceptable performance of the voice conversion system can be verified through ABX listening test and MOS grad. © 2008 Springer-Verlag.