Voice Conversion Based on Cross-Domain Features Using Variational Auto Encoders

August 29, 2018 Β· Declared Dead Β· πŸ› International Symposium on Chinese Spoken Language Processing

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Wen-Chin Huang, Hsin-Te Hwang, Yu-Huai Peng, Yu Tsao, Hsin-Min Wang arXiv ID 1808.09634 Category eess.AS: Audio & Speech Cross-listed cs.CL, cs.LG, cs.SD Citations 48 Venue International Symposium on Chinese Spoken Language Processing Last Checked 6 months ago
Abstract
An effective approach to non-parallel voice conversion (VC) is to utilize deep neural networks (DNNs), specifically variational auto encoders (VAEs), to model the latent structure of speech in an unsupervised manner. A previous study has confirmed the ef- fectiveness of VAE using the STRAIGHT spectra for VC. How- ever, VAE using other types of spectral features such as mel- cepstral coefficients (MCCs), which are related to human per- ception and have been widely used in VC, have not been prop- erly investigated. Instead of using one specific type of spectral feature, it is expected that VAE may benefit from using multi- ple types of spectral features simultaneously, thereby improving the capability of VAE for VC. To this end, we propose a novel VAE framework (called cross-domain VAE, CDVAE) for VC. Specifically, the proposed framework utilizes both STRAIGHT spectra and MCCs by explicitly regularizing multiple objectives in order to constrain the behavior of the learned encoder and de- coder. Experimental results demonstrate that the proposed CD- VAE framework outperforms the conventional VAE framework in terms of subjective tests.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Audio & Speech

Died the same way β€” πŸ‘» Ghosted