用可学习小波与Mamba结构改进扩散模型，实现可控乐谱生成
Mamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music Generation
- 将乐谱转为钢琴卷帘图，结合Transformer-Mamba块和可学习小波变换
- 通过无分类器引导生成指定和弦的音乐，在音质和可控性上超越基线
- 适合音乐生成、可控创作与跨模态生成研究者使用
扩散模型在图像生成中表现优异，但其在符号音乐生成中的应用仍较少。因符号音乐通常以离散事件序列表示，标准扩散模型难以处理。本文将符号音乐表示为类图像的钢琴卷帘图，使扩散模型可用于音乐生成。同时提出新型扩散模型，融合提出的Transformer-Mamba模块与可学习小波变换，并采用无分类器引导实现目标和弦的可控生成。评估显示，该方法在音乐质量与可控性方面均优于强基线，在钢琴卷帘生成任务中表现突出。代码已开源。
原文摘要 · Abstract (English)
The recent surge in the popularity of diffusion models for image synthesis has attracted new attention to their potential for generation tasks in other domains. However, their applications to symbolic music generation remain largely under-explored because symbolic music is typically represented as sequences of discrete events and standard diffusion models are not well-suited for discrete data. We represent symbolic music as image-like pianorolls, facilitating the use of diffusion models for the generation of symbolic music. Moreover, this study introduces a novel diffusion model that incorporates our proposed Transformer-Mamba block and learnable wavelet transform. Classifier-free guidance is utilised to generate symbolic music with target chords. Our evaluation shows that our method achieves compelling results in terms of music quality and controllability, outperforming the strong baseline in pianoroll generation. Our code is available at https://github.com/jinchengzhanggg/proffusion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。