The UFRJ Entry for the Voice Conversion Challenge 2020

Victor P. da Costa, Ranniery Maia, Igor M. Quintanilha, Sergio L. Netto, Luiz W. P. Biscainho


This paper presents our system submitted to the Task 1 of the 2020 edition of the voice conversion challenge (VCC), based on CycleGAN to convert mel-spectograms and MelGAN to synthesize converted speech. CycleGAN is a GAN-based morphing network that uses a cyclic reconstruction cost to allow training with non-parallel corpora. MelGAN is a GAN based non-autoregressive neural vocoder that uses a multi-scale discriminator to efficiently capture complexities of speech signals and achieve high quality signals with extremely fast generation. In the VCC 2020 evaluation our system achieved mean opinion scores of 1.92 for English listeners and 1.81 for Japanese listeners, and averaged similarity score of 2.51 for English listeners and 2.59 for Japanese listeners. The results suggest that possibly the use of neural vocoders to represent converted speech is a problem that demand specific training strategies and the use of adaptation techniques.


 DOI: 10.21437/VCC_BC.2020-29

Cite as: Costa, V.P.D., Maia, R., Quintanilha, I.M., Netto, S.L., Biscainho, L.W.P. (2020) The UFRJ Entry for the Voice Conversion Challenge 2020. Proc. Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020, 184-188, DOI: 10.21437/VCC_BC.2020-29.


@inproceedings{Costa2020,
  author={Victor P. da Costa and Ranniery Maia and Igor M. Quintanilha and Sergio L. Netto and Luiz W. P. Biscainho},
  title={{The UFRJ Entry for the Voice Conversion Challenge 2020}},
  year=2020,
  booktitle={Proc. Joint Workshop for the Blizzard Challenge and Voice Conversion Challenge 2020},
  pages={184--188},
  doi={10.21437/VCC_BC.2020-29},
  url={http://dx.doi.org/10.21437/VCC_BC.2020-29}
}