We present in this paper a voice conversion (VC) method for a person with an articulation disorder resulting from\nathetoid cerebral palsy. The movement of such speakers is limited by their athetoid symptoms, and their consonants\nare often unstable or unclear, which makes it difficult for them to communicate. In this paper, exemplar-based\nspectral conversion using nonnegative matrix factorization (NMF) is applied to a voice with an articulation disorder. To\npreserve the speaker�s individuality, we used an individuality-preserving dictionary that is constructed from the source\nspeaker�s vowels and target speaker�s consonants. Using this dictionary, we can create a natural and clear voice\npreserving their voice�s individuality. Experimental results indicate that the performance of NMF-based VC is\nconsiderably better than conventional GMM-based VC.
Loading....