音乐基础模型是否以螺旋结构嵌入音高?
Do Music Foundation Models Embed Pitch in Helical Structure?
浏览论文内容
中文总结 AI 辅助
该研究分析音乐基础模型的中间表征,发现其音高表征形成反映八度周期性的螺旋结构,且结构特征随模型和输入声学特性变化,为阐明模型内部机制提供新方法。
中文摘要 AI 辅助
本研究分析音乐基础模型(MFMs)的中间表征,报告其用于表示音高信息的几何结构。通过向训练后的MFMs输入孤立音符并分析主成分,发现表征形成反映音高八度周期性的螺旋结构。此外,该螺旋结构的清晰度与几何特征不仅随模型变化,还随输入信号的声学特性变化,为阐明MFMs内部机制提供了新方法。
英文摘要
This study analyzes the intermediate representations of music foundation models (MFMs) and reports the geometric structures used to represent pitch information. By inputting isolated musical notes into trained MFMs and analyzing their principal components, we reveal that the representations form a helical structure reflecting the octave periodicity of pitch. Furthermore, we show that the clarity and geometry of this helical structure vary not only across models but also with the acoustic properties of the input signals. Our analysis provides a novel approach for clarifying the internal mechanisms of MFMs.