AVQVC: One-shot Voice Conversion By Vector Quantization With Applying Contrastive Learning

Abstract

Voice Conversion(VC) refers to changing the timbre of a speech while retaining the discourse content. Recently, many works have focused on disentangle-based learning techniques to separate the timbre and the linguistic content information from a speech signal. Once successful, voice conversion will be feasible and straightforward. This paper proposed a novel one-shot voice conversion framework based on vector quantization voice conversion (VQVC) and AutoVC, called AVQVC. A new training method is applied to VQVC to separate content and timbre information from speech more effectively. The result shows that this approach has better performance than VQVC in separating content and timbre to improve the sound quality of generated speech.

Stats

• citations44
• S2 citations—
• github stars0
• HF likes0
• heat score12.40
• arxiv keytang2022avqvc

Related papers

• VQVC+: One-shot Voice Conversion By Vector Quantization And U-net Architecture (2020)13.34
• VQMIVC: Vector Quantization And Mutual Information-based Unsupervised Speech Representation Disentanglement For One-shot Voice Conversion (2021)20.31
• Speech Representation Disentanglement With Adversarial Mutual Information Learning For One-shot Voice Conversion (2022)11.08
• QR-VC: Leveraging Quantization Residuals For Linear Disentanglement In Zero-shot Voice Conversion (2024)0.00
• Zero-shot Voice Conversion Via Self-supervised Prosody Representation Learning (2021)6.34
• Learning Disentangled Speech Representations With Contrastive Learning And Time-invariant Retrieval (2024)5.84
• VCVTS: Multi-speaker Video-to-speech Synthesis Via Cross-modal Knowledge Transfer From Voice Conversion (2022)6.77
• Vec-tok-vc+: Residual-enhanced Robust Zero-shot Voice Conversion With Progressive Constraints In A Dual-mode Training Strategy (2024)3.58