RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction
This work addresses efficiency bottlenecks for real-time audio generation applications, representing an incremental improvement over existing diffusion models.
The paper tackles the latency issue in audio waveform reconstruction from Mel-spectrograms or acoustic tokens by introducing RFWave, a multi-band Rectified Flow method that achieves high-fidelity reconstruction with only 10 sampling steps, enabling audio generation up to 160 times faster than real-time on a GPU.
Recent advancements in generative modeling have significantly enhanced the reconstruction of audio waveforms from various representations. While diffusion models are adept at this task, they are hindered by latency issues due to their operation at the individual sample point level and the need for numerous sampling steps. In this study, we introduce RFWave, a cutting-edge multi-band Rectified Flow approach designed to reconstruct high-fidelity audio waveforms from Mel-spectrograms or discrete acoustic tokens. RFWave uniquely generates complex spectrograms and operates at the frame level, processing all subbands simultaneously to boost efficiency. Leveraging Rectified Flow, which targets a straight transport trajectory, RFWave achieves reconstruction with just 10 sampling steps. Our empirical evaluations show that RFWave not only provides outstanding reconstruction quality but also offers vastly superior computational efficiency, enabling audio generation at speeds up to 160 times faster than real-time on a GPU. An online demonstration is available at: https://rfwave-demo.github.io/rfwave/.