VoiceGrad: Non-Parallel Any-to-Many Voice Conversion with Annealed Langevin Dynamics

Abstract

In this paper, we propose a non-parallel any-to-many voice conversion (VC) method termed VoiceGrad. Inspired by WaveGrad, a recently introduced novel waveform generation method, VoiceGrad is based upon the concepts of score matching and Langevin dynamics. It uses weighted denoising score matching to train a score approximator, a fully convolutional network with a U-Net structure designed to predict the gradient of the log density of the speech feature sequences of multiple speakers, and performs VC by using annealed Langevin dynamics to iteratively update an input feature sequence towards the nearest stationary point of the target distribution based on the trained score approximator network. Thanks to the nature of this concept, VoiceGrad enables any-to-many VC, a VC scenario in which the speaker of input speech can be arbitrary, and allows for non-parallel training, which requires no parallel utterances or transcriptions.

For more details on the baseline method used for comparison, please refer to our article in arXiv:2008.12604

References in corpus (4)

• NICE: Non-linear Independent Components Estimation
• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
• SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
• Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining

Cited by in corpus (3)

• Gotta Go Fast When Generating Data with Score-Based Models
• FastS2S-VC: Streaming Non-Autoregressive Sequence-to-Sequence Voice Conversion
• Generative Probabilistic Image Colorization