Baseline System of Voice Conversion Challenge 2020 with Cyclic Variational Autoencoder and Parallel WaveGAN

TL;DR

This paper introduces a baseline voice conversion system combining cyclic variational autoencoder and Parallel WaveGAN, demonstrating effective performance on VCC 2020 tasks with open-source implementation.

Contribution

It presents a novel nonparallel voice conversion system using CycleVAE and PWG, applicable to both intra- and cross-lingual tasks, with publicly available code.

Findings

Achieved MOS of 2.87 for naturalness in Task 1

Attained 75.37% speaker similarity in Task 1

Reached MOS of 2.56 and 56.46% similarity in Task 2

Abstract

In this paper, we present a description of the baseline system of Voice Conversion Challenge (VCC) 2020 with a cyclic variational autoencoder (CycleVAE) and Parallel WaveGAN (PWG), i.e., CycleVAEPWG. CycleVAE is a nonparallel VAE-based voice conversion that utilizes converted acoustic features to consider cyclically reconstructed spectra during optimization. On the other hand, PWG is a non-autoregressive neural vocoder that is based on a generative adversarial network for a high-quality and fast waveform generator. In practice, the CycleVAEPWG system can be straightforwardly developed with the VCC 2020 dataset using a unified model for both Task 1 (intralingual) and Task 2 (cross-lingual), where our open-source implementation is available at https://github.com/bigpon/vcc20_baseline_cyclevae. The results of VCC 2020 have demonstrated that the CycleVAEPWG baseline achieves the following: 1) a mean opinion score (MOS) of 2.87 in naturalness and a speaker similarity percentage (Sim) of 75.37% for Task 1, and 2) a MOS of 2.56 and a Sim of 56.46% for Task 2, showing an approximately or nearly average score for naturalness and an above average score for speaker similarity.