End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions
arXiv:2205.09784 · doi:10.21437/Interspeech.2023-2298
Abstract
Zero-shot voice conversion is becoming an increasingly popular research topic, as it promises the ability to transform speech to sound like any speaker. However, relatively little work has been done on end-to-end methods for this task, which are appealing because they remove the need for a separate vocoder to generate audio from intermediate features. In this work, we propose LVC-VC, an end-to-end zero-shot voice conversion model that uses location-variable convolutions (LVCs) to jointly model the conversion and speech synthesis processes. LVC-VC utilizes carefully designed input features that have disentangled content and speaker information, and it uses a neural vocoder-like architecture that utilizes LVCs to efficiently combine them and perform voice conversion while directly synthesizing time domain audio. Experiments show that our model achieves especially well balanced performance between voice style transfer and speech intelligibility compared to several baselines.
INTERSPEECH 2023
References in corpus (9)
- WaveNet: A Generative Model for Raw Audio
- HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
- MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
- In defence of metric learning for speaker recognition
- AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
- F0-consistent many-to-many non-parallel voice conversion via conditional autoencoder
- Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020
- Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning
- LVCNet: Efficient Condition-Dependent Modeling Network for Waveform Generation