Individuality-Preserving Voice Conversion for Articulation Disorders Using Locality-Constrained NMF

We present in this paper a voice conversion (VC) method for a person with an articulation disorder resulting from athetoid cerebral palsy. The movements of such speakers are limited by their athetoid symptoms, and their consonants are often unstable or unclear, which makes it difficult for them to communicate. In this paper, exemplar-based spectral conversion using Nonnegative Matrix Factorization (NMF) is applied to a voice with an articulation disorder. In order to preserve the speaker’s individuality, we use a combined dictionary that was constructed from the source speaker’s vowels and target speaker’s consonants. Also, in order to avoid an unclear converted voice, which is constructed using the combined dictionary, we used localityconstrained NMF. The effectiveness of this method was confirmed by comparing its effectiveness with that of a conventional Gaussian Mixture Model (GMM)-based method.