The rapid advancement of AI music generators highlights the urgent need for reliable Synthetic Song Detection (SSD). Existing SSD methods often rely on low-level artifacts or fixed feature assumptions, struggling to capture generator-agnostic cues. To address this, we propose Sofia (Synthetic-song detection framework via music features), a flexible framework that models music-intrinsic attributes via feature-specific experts and an adaptive Mixture-of-Experts (MoE) module. By configuring Sofia with representative Vocal, Audio-effect, Global structure features, and their combinations, we present their individual and complementary contributions. To comprehensively evaluate our framework, we further construct MUSIC8K, a challenging benchmark featuring lastest emerging generators and realistic audio perturbations. Experiments show that Sofia learns generator-agnostic representations from music-intrinsic features, improving the F1 score by 18.5 points over the strongest baseline on MUSIC8K-O while maintaining strong robustness.

翻译：AI音乐生成器的快速发展凸显了对可靠合成歌曲检测（Synthetic Song Detection，SSD）的迫切需求。现有的SSD方法通常依赖低层级伪迹或固定的特征假设，难以捕捉与生成器无关的线索。针对这一问题，我们提出Sofia（基于音乐特征的合成歌曲检测框架），该框架通过特征特定专家和自适应混合专家（Mixture-of-Experts，MoE）模块建模音乐内在属性。通过配置Sofia使用代表性的人声、音频效果、全局结构特征及其组合，我们展示了这些特征的独立及互补贡献。为全面评估该框架，我们进一步构建了包含最新涌现的生成器和真实音频扰动的挑战性基准数据集MUSIC8K。实验表明，Sofia从音乐内在特征中学习到与生成器无关的表征，在MUSIC8K-O上将F1分数较最强基线提升18.5个百分点，同时保持强鲁棒性。