PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior

TL;DR

PriorGrad introduces a data-dependent adaptive prior to conditional diffusion models, significantly enhancing speech synthesis quality, convergence speed, and robustness by aligning the prior more closely with data statistics.

Contribution

It proposes an adaptive prior for diffusion models that improves efficiency and performance in speech synthesis tasks, with theoretical analysis and empirical validation.

Findings

Faster convergence and inference in speech synthesis models.

Improved perceptual quality and robustness.

Effective with smaller network capacities.

Abstract

Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density. The framework defines the prior noise as a standard Gaussian distribution, whereas the corresponding data distribution may be more complicated than the standard Gaussian distribution, which potentially introduces inefficiency in denoising the prior noise into the data sample because of the discrepancy between the data and the prior. In this paper, we propose PriorGrad to improve the efficiency of the conditional diffusion model for speech synthesis (for example, a vocoder using a mel-spectrogram as the condition) by applying an adaptive prior derived from the data statistics based on the conditional information. We formulate the training and sampling procedures of PriorGrad and demonstrate the advantages of an adaptive prior through a theoretical analysis. Focusing on the speech synthesis domain, we consider the recently proposed diffusion-based speech generative models based on both the spectral and time domains and show that PriorGrad achieves faster convergence and inference with superior performance, leading to an improved perceptual quality and robustness to a smaller network capacity, and thereby demonstrating the efficiency of a data-dependent adaptive prior.