Diffusion models have demonstrated promising results in text-to-audio generation tasks. However, their practical usability is hindered by slow sampling speeds, limiting their applicability in high-throughput scenarios. To address this challenge, progressive distillation methods have been effective in producing more compact and efficient models. Nevertheless, these methods encounter issues with unbalanced weights at both high and low noise levels, potentially impacting the quality of generated samples. In this paper, we propose the adaptation of the progressive distillation method to text-to-audio generation tasks and introduce the Balanced SNR-Aware~(BSA) method, an enhanced loss-weighting mechanism for diffusion distillation. The BSA method employs a balanced approach to weight the loss for both high and low noise levels. We evaluate our proposed method on the AudioCaps dataset and report experimental results showing superior performance during the reverse diffusion process compared to previous distillation methods with the same number of sampling steps. Furthermore, the BSA method allows for a significant reduction in sampling steps from 200 to 25, with minimal performance degradation when compared to the original teacher models.

翻译：扩散模型在文本到音频生成任务中展现了良好效果，但其采样速度较慢，限制了在高吞吐量场景下的实际应用性。为解决这一挑战，渐进式蒸馏方法已有效生成更紧凑高效的模型。然而，这些方法在高低噪声水平下存在权重不平衡问题，可能影响生成样本质量。本文提出将渐进式蒸馏方法适配至文本到音频生成任务，并引入平衡信噪比感知（BSA）方法——一种针对扩散蒸馏的增强型损失权重机制。BSA方法采用平衡策略对高低噪声水平的损失进行加权。我们在AudioCaps数据集上评估所提方法，实验结果表明，在相同采样步数下，该方法在逆向扩散过程中性能优于以往蒸馏方法。此外，BSA方法能将采样步数从200步显著缩减至25步，且与原始教师模型相比性能退化极小。