cs.SDMay 28, 2025

AudioTurbo: Fast Text-to-Audio Generation with Rectified Diffusion

Authors: Junqi Zhao, Jinheng Zhao, Haohe Liu, Yun Chen, Lu Han, Haoyang Zhang, Xubo Liu, Mark Plumbley, 

Organizations: Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK · Laboratory of Noise and Audio Research, Institute of Acoustics, Chinese Academy of Sciences, China

Abstract

Diffusion models have significantly improved the quality and diversity of text-to-audio (TTA) generation but are hindered by slow inference speed. Recent flow-based approaches have been explored for accelerating TTA generation. However, these approaches typically rely on dedicated flow-based generative frameworks and do not directly exploit existing pre-trained diffusion-based TTA models. To address this limitation while leveraging the strong generative capabilities of pre-trained diffusion models, we integrate rectified diffusion into these models to improve TTA generation efficiency. Specifically, we propose AudioTurbo, which learns first-order approximate ordinary differential equation (ODE) paths from deterministic noise-sample pairs generated by a pre-trained TTA model. Experiments show that our approach outperforms a flow-matching-based acceleration model in both generation quality and inference speed.

Figures & tables

Explore similar work

CardsList
  1. SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving

    Mar 9, 2026Ayush Barik, Sofia Stoica, Nikhil Sarda +4Text-to-Audio GenerationDiffusion Model Inference Acceleration

  2. FdAudio: MeanFlow-Anchored Fréchet-Distance Post-Training for One-Step Text-to-Audio Generation

    Jul 11, 2026Kuan-Po Huang, Bo-Ru Lu, Ho-Lam Chung +2Text-to-Audio GenerationFlow Matching