14thAnnual Conference of the International Speech Communication Association

Lyon, France
August 25-29, 2013

Exemplar-Based Individuality-Preserving Voice Conversion for Articulation Disorders in Noisy Environments

Ryo Aihara, Ryoichi Takashima, Tetsuya Takiguchi, Yasuo Ariki

Kobe University, Japan

We present in this paper a noise robust 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 real noisy environments. In this paper, in order to deal with background noise, an input noisy source signal is decomposed into the clean source exemplars and noise exemplars by NMF. Also, to preserve the speaker's individuality, we use a combined dictionary that was constructed from the source speakerfs vowels and target speaker's consonants. The effectiveness of this method was confirmed by comparing its effectiveness with that of a conventional Gaussian Mixture Model (GMM)-based method.

Full Paper

Bibliographic reference.  Aihara, Ryo / Takashima, Ryoichi / Takiguchi, Tetsuya / Ariki, Yasuo (2013): "Exemplar-based individuality-preserving voice conversion for articulation disorders in noisy environments", In INTERSPEECH-2013, 3637-3641.