Parallel And Limited Data Voice Conversion Using Stochastic Variational Deep Kernel Learning

Abstract

Typically, voice conversion is regarded as an engineering problem with limited training data. The reliance on massive amounts of data hinders the practical applicability of deep learning approaches, which have been extensively researched in recent years. On the other hand, statistical methods are effective with limited data but have difficulties in modelling complex mapping functions. This paper proposes a voice conversion method that works with limited data and is based on stochastic variational deep kernel learning (SVDKL). At the same time, SVDKL enables the use of deep neural networks' expressive capability as well as the high flexibility of the Gaussian process as a Bayesian and non-parametric method. When the conventional kernel is combined with the deep neural network, it is possible to estimate non-smooth and more complex functions. Furthermore, the model's sparse variational Gaussian process solves the scalability problem and, unlike the exact Gaussian process, allows for the

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyjafaryani2023parallel

Related papers

• Semi-supervised Voice Conversion With Amortized Variational Inference (2019)3.58
• Conditional Deep Hierarchical Variational Autoencoder For Voice Conversion (2021)0.00
• Diffusion-based Voice Conversion With Fast Maximum Likelihood Sampling Scheme (2021)0.00
• Stargan-zsvc: Towards Zero-shot Voice Conversion In Low-resource Contexts (2021)3.58
• Starganv2-vc: A Diverse, Unsupervised, Non-parallel Framework For Natural-sounding Voice Conversion (2021)13.70
• Towards Low-resource Stargan Voice Conversion Using Weight Adaptive Instance Normalization (2020)7.81
• Stargan-vc2: Rethinking Conditional Methods For Stargan-based Voice Conversion (2019)0.00
• Stargan-vc: Non-parallel Many-to-many Voice Conversion With Star Generative Adversarial Networks (2018)18.09