VCVictor P. da Costa

Victor P. da Costa

*This is an algorithmically generated author record based on publicly available information.

Victor P. da Costa has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Pitch-Controlled End-to-End Voice Conversion System for Brazilian Portuguese

    by Universidade Federal do Rio de Janeiro, da Costa Vitor P., Netto Sergio L., Biscainho Luiz Wagner P, Maia Ranniery, Universidade Federal do Rio Grande do Norte

    Speech conversion is a technique that modifies the identity of the voice in a speech signal without changing the spoken content. Accurate pitch conversion is a requirement the best speech conversion systems must address, as this characteristic is essential to the correct identification of the target speaker. This work proposes a pitch-controlled end-to-end voice conversion model that combines state-of-the-art ideas from both speaking and singing voice conversion with a novel cost function to ensure artifact-free pitch tracking. The model is trained in Brazilian Portuguese, overcoming the lack of high-quality data by improving a large but flawed dataset with filtering operation. Our model mostly outperforms other popular open source models in both listening tests and objective measurements. In particular, on a 5-point MOS, we obtained the highest speaker similarity score (4.05), and a naturalness score of 3.48, second only to a system whose similarity score was 2.62.

  • Open Access

    The UFRJ Entry for the Voice Conversion Challenge 2020

    by 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.