VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture

Abstract

Voice conversion (VC) is a task that transforms the source speaker's timbre, accent, and tones in audio into another one's while preserving the linguistic content. It is still a challenging work, especially in a one-shot setting. Auto-encoder-based VC methods disentangle the speaker and the content in input speech without given the speaker's identity, so these methods can further generalize to unseen speakers. The disentangle capability is achieved by vector quantization (VQ), adversarial training, or instance normalization (IN). However, the imperfect disentanglement may harm the quality of output speech. In this work, to further improve audio quality, we use the U-Net architecture within an auto-encoder-based VC system. We find that to leverage the U-Net architecture, a strong information bottleneck is necessary. The VQ-based method, which quantizes the latent vectors, can serve the purpose. The objective and the subjective evaluations show that the proposed method performs well in both audio naturalness and speaker similarity.

References in corpus (9)

• Instance Normalization: The Missing Ingredient for Fast Stylization
• Neural Discrete Representation Learning
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
• AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
• MelNet: A Generative Model for Audio in the Frequency Domain
• F0-consistent many-to-many non-parallel voice conversion via conditional autoencoder
• Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion
• Score and Lyrics-Free Singing Voice Generation

Cited by in corpus (6)

• "Hello, It's Me": Deep Learning-based Speech Synthesis Attacks in the Real World
• An Overview of Voice Conversion and its Challenges: From Statistical Modeling to Deep Learning
• NoiseVC: Towards High Quality Zero-Shot Voice Conversion
• The Multi-speaker Multi-style Voice Cloning Challenge 2021
• Learning in your voice: Non-parallel voice conversion based on speaker consistency loss
• Zero-shot Voice Conversion via Self-supervised Prosody Representation Learning