用五种方法生成和弦伴奏旋律，发现先生成低音效果最好。
Chord-conditioned Melody and Bass Generation
- 对比五种基于Transformer的和弦条件生成策略
- 先生成低音的模型在和弦音使用上更符合音乐理论
- 适合对音乐风格准确性要求高的生成任务
我们评估了五种基于Transformer的和弦条件旋律与低音生成策略，采用一系列基于音乐理论的度量标准，涵盖音高内容、音程大小及和弦音使用情况。所评估模型包括：(1) 无和弦条件，(2) 独立线性和弦条件生成，(3) 低音优先的和弦条件生成，(4) 旋律优先的和弦条件生成，(5) 和弦条件联合生成。结果表明，加入和弦条件可有效提升风格化音高内容与和弦音使用的再现能力，尤其在低音优先模型中表现显著。
原文摘要 · Abstract (English)
We evaluate five Transformer-based strategies for chord-conditioned melody and bass generation using a set of music theory-motivated metrics capturing pitch content, pitch interval size, and chord tone usage. The evaluated models include (1) no chord conditioning, (2) independent line chord-conditioned generation, (3) bass-first chord-conditioned generation, (4) melody-first chord-conditioned generation, and (5) chord-conditioned co-generation. We show that chord-conditioning improves the replication of stylistic pitch content and chord tone usage characteristics, particularly for the bass-first model.
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。