Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks

We propose a parallel-data-free voice conversion (VC)method that can learn a mapping from source to target speech without relying on parallel data. The proposed method is generalpurpose, high quality, and parallel-data-free, which works without any extra data, modules, or alignment procedure. It is also noteworthy that it avoids over-smoothing, which occurs in many conventional statistical model-based VC methods. Our method uses a cycle-consistent adversarial network (CycleGAN) with gated convolutional neural networks (CNNs) and an identity-mapping loss. The CycleGAN learns forward and inverse mappings simultaneously using adversarial and cycle-consistency losses. This makes it possible to find an optimal pseudo pair from unpaired data. Furthermore, the adversarial loss contributes to reducing over-smoothing of the converted feature sequence. We configure a CycleGAN with gated CNNs and train it with an identity-mapping loss. This allows the mapping function to capture sequential and hierarchical structures while preserving linguistic information. We evaluated our method on a parallel-data-free VC task. An objective evaluation showed that the converted feature sequence was near natural in terms of global variance and modulation spectra. A subjective evaluation showed that the quality of the converted speech was comparable to that obtained with the GMM-based method under advantageous conditions with parallel data.