Novel Inter Mixture Weighted GMM Posteriorgram for DNN and GAN-based Voice Conversion
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, pp. 1776.0-1781.0, 2018.
Voice Conversion (VC) requires an alignment of the spectral features before learning the mapping function, due to the speaking rate variations across the source and target speakers. To address this issue, the idea of training two parallel networks with the use of speaker-independent representation was proposed. In this paper, we explore t...More
Full Text (Upload PDF)
PPT (Upload PPT)