Voice conversion by combining frequency warping with unit selection

In this paper, we propose a novel voice conversion method by combining frequency warping and unit selection to improve the similarity to target speaker. We use frequency warping to get the warped source spectrum, which will be used as estimated target for later unit selection of the target speaker's spectrum. Such estimated target can preserve the natural transition of human's speech. Then, part of the warped source spectrum is replaced by the selected target speaker's real spectrum before reconstructing the converted speech to reduce the difference in detailed spectrum. TC- STAR 2007 voice conversion evaluation results show that the proposed method can achieve about 20% improvement in similarity score compared to only frequency warping.