arXiv：cs.AI· Jincheng Zhang, Gy\"orgy Fazekas, Charalampos Saitis·· 17 小时前
Fast Diffusion-GAN 模型：用 15 步去噪生成带情感的符号音乐
Fast Diffusion-GAN Model for Generating Symbolic Music with Emotions
AI 导读
研究者提出一种融合 GAN 的扩散模型，用于生成带指定情感的符号音乐，缓解扩散模型采样慢的问题。该方法将符号音乐表示为带力度值的类图像 pianoroll，并用变分自编码器获取其潜在表示来训练扩散模型。模型仅需 15 步去噪即可生成高质量音乐，而多数符号音乐扩散模型需数百至数千步。
正文
Abstract:Diffusion models have shown promising results for a wide range of generative tasks with continuous data, such as image and audio synthesis. However, little progress has been made on using diffusion models to generate symbolic music since this class of generative models struggles with discrete data while its iterative sampling process is computationally expensive. In this work, we propose a diffusion model integrated with a Generative Adversarial Network, aiming to mitigate the slow sampling drawback of diffusion models applied to symbolic music generation. We enable the use of diffusion model by representing symbolic music as image-like pianorolls with velocity values instead of discrete event tokens and then used a Variational Autoencoder to obtain their latent representations to train the proposed diffusion model. Our results demonstrate the successful control of our diffusion model to generate symbolic music with a desired emotion. Our model uses merely 15 denoising diffusion steps to produce high-quality music, while most diffusion models for symbolic music generation require hundreds or thousands of steps.
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2310.14040 [cs.SD] |
| (or arXiv:2310.14040v2 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2310.14040 arXiv-issued DOI via DataCite |
Submission history
From: Jincheng Zhang [view email]
[v1]
Sat, 21 Oct 2023 15:35:43 UTC (987 KB)
[v2]
Sun, 11 Oct 2026 12:00:16 UTC (1,677 KB)
来源：arXiv：cs.AI · arxiv.org