AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

Abstract

Non-parallel many-to-many voice conversion, as well as zero-shot voice conversion, remain under-explored areas. Deep style transfer algorithms, such as generative adversarial networks (GAN) and conditional variational autoencoder (CVAE), are being applied as new solutions in this field. However, GAN training is sophisticated and difficult, and there is no strong evidence that its generated speech is of good perceptual quality. On the other hand, CVAE training is simple but does not come with the distribution-matching property of a GAN. In this paper, we propose a new style transfer scheme that involves only an autoencoder with a carefully designed bottleneck. We formally show that this scheme can achieve distribution-matching style transfer by training only on a self-reconstruction loss. Based on this scheme, we proposed AUTOVC, which achieves state-of-the-art results in many-to-many voice conversion with non-parallel data, and which is the first to perform zero-shot voice conversion.

To Appear in Thirty-sixth International Conference on Machine Learning (ICML 2019)

References in corpus (5)

• WaveNet: A Generative Model for Raw Audio
• Semi-Supervised Learning with Deep Generative Models
• Deep Voice: Real-time Neural Text-to-Speech
• Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks
• Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder

Cited by in corpus (7)

• F0-consistent many-to-many non-parallel voice conversion via conditional autoencoder
• TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training
• VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture
• StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts
• SpeechNet: A Universal Modularized Model for Speech Processing Tasks
• ConVoice: Real-Time Zero-Shot Voice Style Transfer with Convolutional Network
• An Improved StarGAN for Emotional Voice Conversion: Enhancing Voice Quality and Data Augmentation