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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyqian2019autovc

Related papers

• Convoice: Real-time Zero-shot Voice Style Transfer With Convolutional Network (2020)0.00
• F0-consistent Many-to-many Non-parallel Voice Conversion Via Conditional Autoencoder (2020)13.17
• GAZEV: Gan-based Zero-shot Voice Conversion Over Non-parallel Speech Corpus (2020)8.60
• Improving Zero-shot Voice Style Transfer Via Disentangled Representation Learning (2021)0.00
• One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation (2021)8.09
• CVC: Contrastive Learning For Non-parallel Voice Conversion (2020)7.50
• ACE-VC: Adaptive And Controllable Voice Conversion Using Explicitly Disentangled Self-supervised Speech Representations (2023)0.00
• Pureformer-vc: Non-parallel One-shot Voice Conversion With Pure Transformer Blocks And Triplet Discriminative Training (2024)0.00