VoiceGrad: Non-Parallel Any-to-Many Voice Conversion with Annealed Langevin Dynamics
arXiv:2010.02977
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.
arXiv commentFor more details on the baseline method used for comparison, please refer to our article in arXiv:2008.12604
References in corpus (15)
- Auto-Encoding Variational Bayes
- Denoising Diffusion Probabilistic Models
- Neural Discrete Representation Learning
- NICE: Non-linear Independent Components Estimation
- Generative Modeling by Estimating Gradients of the Data Distribution
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
- MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
- SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
- Improved Techniques for Training Score-Based Generative Models
- Efficient Neural Audio Synthesis
- ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech
- Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion
- Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining
- FloWaveNet : A Generative Flow for Raw Audio
- Many-to-Many Voice Transformer Network