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.
翻译:语音转换是一项常见的语音合成任务,可根据特定现实世界的情景以不同方式加以解决。 最具有挑战性的任务通常被称为一发多发语音转换。 在最普通的情况下,当源和目标发言者都不属于培训数据集时,最普通情况下只复制一个参考声音。 我们提出了一个基于传播概率模型的可扩展性高品质解决方案,并展示其优于最先进的一发语音转换方法的质量。 此外,我们注重实时应用,调查一般原则,使传播模型更快,同时保持高水平的合成质量。 因此,我们开发了一个新的小巧差异方程式解决方案,适合各种扩散模型类型和通过实验研究显示的基因化任务,并通过理论分析证明其合理性。