Scyclone: High-Quality and Parallel-Data-Free Voice Conversion Using Spectrogram and Cycle-Consistent Adversarial Networks
Abstract
This paper proposes Scyclone, a high-quality voice conversion (VC) technique without parallel data training. Scyclone improves speech naturalness and speaker similarity of the converted speech by introducing CycleGAN-based spectrogram conversion with a simplified WaveRNN-based vocoder. In Scyclone, a linear spectrogram is used as the conversion features instead of vocoder parameters, which avoids quality degradation due to extraction errors in fundamental frequency and voiced/unvoiced parameters. The spectrogram of source and target speakers are modeled by modified CycleGAN networks, and the waveform is reconstructed using the simplified WaveRNN with a single Gaussian probability density function. The subjective experiments with completely unpaired training data show that Scyclone is significantly better than CycleGAN-VC2, one of the existing state-of-the-art parallel-data-free VC techniques.
Cite
@article{arxiv.2005.03334,
title = {Scyclone: High-Quality and Parallel-Data-Free Voice Conversion Using Spectrogram and Cycle-Consistent Adversarial Networks},
author = {Masaya Tanaka and Takashi Nose and Aoi Kanagaki and Ryohei Shimizu and Akira Ito},
journal= {arXiv preprint arXiv:2005.03334},
year = {2020}
}