Scyclone: High-Quality and Parallel-Data-Free Voice Conversion Using Spectrogram and Cycle-Consistent Adversarial Networks
Masaya Tanaka (Tokyo University of Agriculture and Technology)Takashi Nose (Tohoku University)
Aoi Kanagaki (Tohoku University)
Ryouhei Shimizu (The University of Tokyo)
Akira Ito (Tohoku University)
| 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. |
| Target speaker | Ayanami | F009 |
|---|---|---|
| Source (natural) | ||
| Target (natural) | ||
| Target (vocoded) | ||
| CycleGAN-VC2 | ||
| Scyclone |
| Target speaker | Ayanami | F009 |
|---|---|---|
| Source (natural) | ||
| Target (natural) | ||
| Target (vocoded) | ||
| CycleGAN-VC2 | ||
| Scyclone |