基于规则的音乐约束对齐语言模型用于歌词到旋律生成
Aligning Language Models for Lyric-to-Melody Generation with Rule-Based Musical Constraints
AI总结：
本文提出基于规则的音乐约束对齐框架，通过DPO和KTO优化减少旋律生成中的约束违规，提升音乐性和连贯性。
摘要：
大型语言模型（LLMs）在歌词到旋律生成中表现出潜力，但通过监督微调（SFT）训练的模型常产生音乐上不合理的旋律，如节奏差和不合适的声域，我们称之为
英文摘要：
Large Language Models (LLMs) show promise in lyric-to-melody generation, but models trained with Supervised Fine-Tuning (SFT) often produce musically implausible melodies with issues like poor rhythm and unsuitable vocal ranges, a phenomenon we term "constraint violation". To address this, we propose a novel alignment framework that instills musical knowledge without human annotation. We define rule-based musical constraints to automatically generate a preference dataset from an SFT model's outputs. The model is then aligned through a sequential process, first using Direct Preference Optimization (DPO) on paired preference data, followed by Kahneman-Tversky Optimization (KTO) on unpaired negative samples. Experimental results demonstrate that our aligned model substantially reduces rule violations and outperforms strong baselines in both objective and subjective evaluations, generating melodies with substantially improved musicality and coherence. An interactive demo with audio comparisons is available at https://arain233.github.io/AligningMelody-demo.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
