VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion
This improves voice conversion technology for applications like speech synthesis and editing, though it appears incremental as it builds on existing disentanglement methods.
The paper tackles the problem of one-shot voice conversion by addressing content leakage into speaker representations, using vector quantization and mutual information to disentangle speech representations, achieving higher speech naturalness and speaker similarity than state-of-the-art systems.
One-shot voice conversion (VC), which performs conversion across arbitrary speakers with only a single target-speaker utterance for reference, can be effectively achieved by speech representation disentanglement. Existing work generally ignores the correlation between different speech representations during training, which causes leakage of content information into the speaker representation and thus degrades VC performance. To alleviate this issue, we employ vector quantization (VQ) for content encoding and introduce mutual information (MI) as the correlation metric during training, to achieve proper disentanglement of content, speaker and pitch representations, by reducing their inter-dependencies in an unsupervised manner. Experimental results reflect the superiority of the proposed method in learning effective disentangled speech representations for retaining source linguistic content and intonation variations, while capturing target speaker characteristics. In doing so, the proposed approach achieves higher speech naturalness and speaker similarity than current state-of-the-art one-shot VC systems. Our code, pre-trained models and demo are available at https://github.com/Wendison/VQMIVC.