arXiv cs.AI· Jincheng Zhang, Gy\"orgy Fazekas, Charalampos Saitis·· 3 天前AI 评分20
快速 Diffusion-GAN 模型：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 Diffusion-GAN 模型用于生成带情感符号音乐，通过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潜在表示，绕开扩散模型处理离散数据的难题。该模型仅需 15 步去噪扩散即可生成高质量音乐，而多数符号音乐扩散模型需要数百甚至数千步，并成功实现对生成音乐情感的控制。
正文 · 原文
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