Music Style Transfer With Diffusion Model
This addresses the need for efficient and high-fidelity multi-style music conversion, though it appears incremental as it builds on existing diffusion model techniques.
The study tackled the problem of multi-to-multi music style transfer, which previous methods handled inefficiently with artifacts and noise, by proposing a diffusion model framework that generates high-quality audio in real-time on consumer GPUs.
Previous studies on music style transfer have mainly focused on one-to-one style conversion, which is relatively limited. When considering the conversion between multiple styles, previous methods required designing multiple modes to disentangle the complex style of the music, resulting in large computational costs and slow audio generation. The existing music style transfer methods generate spectrograms with artifacts, leading to significant noise in the generated audio. To address these issues, this study proposes a music style transfer framework based on diffusion models (DM) and uses spectrogram-based methods to achieve multi-to-multi music style transfer. The GuideDiff method is used to restore spectrograms to high-fidelity audio, accelerating audio generation speed and reducing noise in the generated audio. Experimental results show that our model has good performance in multi-mode music style transfer compared to the baseline and can generate high-quality audio in real-time on consumer-grade GPUs.