Improving Zero-shot Voice Style Transfer Via Disentangled Representation Learning
2021 · Siyang Yuan, Pengyu Cheng, Ruiyi Zhang, et al.
Abstract
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and pre-known speakers. However, zero-shot voice style transfer, which learns from non-parallel data and generates voices for previously unseen speakers, remains a challenging problem. We propose a novel zero-shot voice transfer method via disentangled representation learning. The proposed method first encodes speaker-related style and voice content of each input voice into separated low-dimensional embedding spaces, and then transfers to a new voice by combining the source content embedding and target style embedding through a decoder. With information-theoretic guidance, the style and content embedding spaces are representative and (ideally) independent of each other. On real-world VCTK datasets, our method outperforms other baselines and obtains state-o
Authors
(none)
Tags
Stats
Related papers
- Robust Disentangled Variational Speech Representation Learning For Zero-shot Voice Conversion (2022)10.97
- ZSVC: Zero-shot Style Voice Conversion With Disentangled Latent Diffusion Models And Adversarial Training (2025)0.00
- Zero-shot Voice Conversion Via Self-supervised Prosody Representation Learning (2021)6.34
- ACE-VC: Adaptive And Controllable Voice Conversion Using Explicitly Disentangled Self-supervised Speech Representations (2023)0.00
- Learning Disentangled Speech Representations With Contrastive Learning And Time-invariant Retrieval (2024)5.84
- AUTOVC: Zero-shot Voice Style Transfer With Only Autoencoder Loss (2019)0.00
- Convoice: Real-time Zero-shot Voice Style Transfer With Convolutional Network (2020)0.00
- Speech Representation Disentanglement With Adversarial Mutual Information Learning For One-shot Voice Conversion (2022)11.08