用分层思维生成结构完整多轨电子音乐，支持人机协同创作。
TOMI: Transforming and Organizing Music Ideas for Multi-Track Compositions with Full-Song Structure
- 构建四维空间建模音乐片段、段落、音轨与变换方式
- 生成具备完整歌曲结构的多轨电子音乐，质量优于基线方法
- 可集成到REAPER实现交互式人机共创，适合音乐创作者
层级规划是建模长序列结构的有效方法。本文不仅关注音乐的时间结构层次，更深入探索概念层次：即音乐创意的生成、转换与跨时间空间的组织。为此，我们提出TOMI（Transforming and Organizing Music Ideas）这一深度音乐生成新范式，并基于指令微调的大型语言模型构建了TOMI模型。形式上，通过一个稀疏的四维空间表征多轨编曲过程，维度包括片段（短音频或MIDI段）、段落（时间位置）、音轨（乐器层）和变换（细化方法）。该模型能生成具备完整歌曲结构的多轨电子音乐，并进一步与数字音频工作站REAPER集成，实现人机交互式共创。实验表明，该方法生成的电子音乐在结构连贯性与整体质量上均优于现有基线。
原文摘要 · Abstract (English)
Hierarchical planning is a powerful approach to model long sequences structurally. Aside from considering hierarchies in the temporal structure of music, this paper explores an even more important aspect: concept hierarchy, which involves generating music ideas, transforming them, and ultimately organizing them--across musical time and space--into a complete composition. To this end, we introduce TOMI (Transforming and Organizing Music Ideas) as a novel approach in deep music generation and develop a TOMI-based model via instruction-tuned foundation LLM. Formally, we represent a multi-track composition process via a sparse, four-dimensional space characterized by clips (short audio or MIDI segments), sections (temporal positions), tracks (instrument layers), and transformations (elaboration methods). Our model is capable of generating multi-track electronic music with full-song structure, and we further integrate the TOMI-based model with the REAPER digital audio workstation, enabling interactive human-AI co-creation. Experimental results demonstrate that our approach produces higher-quality electronic music with stronger structural coherence compared to baselines.
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。