AudioTurbo: Fast Text-to-Audio Generation with Rectified Diffusion
This work addresses the inference speed bottleneck for text-to-audio generation, offering a practical improvement for audio synthesis applications, though it is incremental as it builds on existing rectified flow and pre-trained diffusion techniques.
The paper tackles the slow inference speed of diffusion models for text-to-audio generation by integrating pre-trained models with rectified diffusion, resulting in AudioTurbo, which achieves better performance with only 10 sampling steps and reduces inference to 3 steps compared to prior methods.
Diffusion models have significantly improved the quality and diversity of audio generation but are hindered by slow inference speed. Rectified flow enhances inference speed by learning straight-line ordinary differential equation (ODE) paths. However, this approach requires training a flow-matching model from scratch and tends to perform suboptimally, or even poorly, at low step counts. To address the limitations of rectified flow while leveraging the advantages of advanced pre-trained diffusion models, this study integrates pre-trained models with the rectified diffusion method to improve the efficiency of text-to-audio (TTA) generation. Specifically, we propose AudioTurbo, which learns first-order ODE paths from deterministic noise sample pairs generated by a pre-trained TTA model. Experiments on the AudioCaps dataset demonstrate that our model, with only 10 sampling steps, outperforms prior models and reduces inference to 3 steps compared to a flow-matching-based acceleration model.