On combining statistical methods and frequency warping for high-quality voice conversion

In current voice conversion systems, obtaining a high similarity between converted and target voices requires a high degree of signal manipulation, which implies important quality degradation, up to the point that in some cases the quality scores are unacceptable for real-life applications. Indeed, a tradeoff can be observed between the similarity scores and the quality scores achieved by a given voice conversion system. In our previous works we proved that statistical methods and frequency warping transformations could be combined to yield a better similarity-quality balance than conventional systems, due to significant quality improvements. In this paper, two different ways of combining these two approaches are compared through perceptual tests in order to determine the best strategy for high-quality voice conversion. The comparison is made under the same training conditions, using the same speech model and vector dimensions. The results indicate that the Weighted Frequency Warping method is preferred by listeners.