Diffusion-based Voice Conversion With Fast Maximum Likelihood Sampling Scheme
2021 · Vadim Popov, Ivan Vovk, Vladimir Gogoryan, et al.
Abstract
Voice conversion is a common speech synthesis task which can be solved in different ways depending on a particular real-world scenario. The most challenging one often referred to as one-shot many-to-many voice conversion consists in copying the target voice from only one reference utterance in the most general case when both source and target speakers do not belong to the training dataset. We present a scalable high-quality solution based on diffusion probabilistic modeling and demonstrate its superior quality compared to state-of-the-art one-shot voice conversion approaches. Moreover, focusing on real-time applications, we investigate general principles which can make diffusion models faster while keeping synthesis quality at a high level. As a result, we develop a novel Stochastic Differential Equations solver suitable for various diffusion model types and generative tasks as shown through empirical studies and justify it by theoretical analysis.
Authors
(none)
Tags
Stats
Related papers
- Fastvoicegrad: One-step Diffusion-based Voice Conversion With Adversarial Conditional Diffusion Distillation (2024)4.52
- Highly Controllable Diffusion-based Any-to-any Voice Conversion Model With Frame-level Prosody Feature (2023)0.00
- Diff-hiervc: Diffusion-based Hierarchical Voice Conversion With Robust Pitch Generation And Masked Prior For Zero-shot Speaker Adaptation (2023)0.00
- Fastdiff: A Fast Conditional Diffusion Model For High-quality Speech Synthesis (2022)14.35
- Converting Anyone's Voice: End-to-end Expressive Voice Conversion With A Conditional Diffusion Model (2024)5.24
- Parallel And Limited Data Voice Conversion Using Stochastic Variational Deep Kernel Learning (2023)5.84
- An Overview Of Voice Conversion And Its Challenges: From Statistical Modeling To Deep Learning (2020)18.53
- Residual Speaker Representation For One-shot Voice Conversion (2023)0.00