用旋律感知模型和数据集检测音乐抄袭，更精准识别相似片段。
MelodySim: Measuring Melody-aware Music Similarity for Plagiarism Detection
- 通过音符拆分、琶音化等手法生成旋律不变的变体构建数据集。
- 基于MERT编码器的三元组网络在测试集上超越基线模型。
- 适合音乐版权保护、智能作曲工具开发者使用。
我们提出MelodySim，一种用于抄袭检测的旋律感知音乐相似性模型与数据集。首先，我们提出一种新方法构建聚焦旋律相似性的数据集，通过对现有MIDI数据集Slakh2100进行增强，生成每首作品的变体，通过音符拆分、琶音化、少量音轨丢失及重新配器等操作保持旋律一致，用户研究证实正样本确实具有相似旋律，而其他音乐元素显著变化。其次，我们开发了一种分段式旋律相似性检测模型，采用MERT编码器并结合三元组神经网络捕捉旋律相似性，生成的决策矩阵可定位潜在抄袭区域。实验表明，该模型在MelodySim测试集上优于基线模型，能有效识别相似旋律片段。
原文摘要 · Abstract (English)
We propose MelodySim, a melody-aware music similarity model and dataset for plagiarism detection. First, we introduce a novel method to construct a dataset focused on melodic similarity. By augmenting Slakh2100, an existing MIDI dataset, we generate variations of each piece while preserving the melody through modifications such as note splitting, arpeggiation, minor track dropout, and re-instrumentation. A user study confirms that positive pairs indeed contain similar melodies, while other musical tracks are significantly changed. Second, we develop a segment-wise melodic-similarity detection model that uses a MERT encoder and applies a triplet neural network to capture melodic similarity. The resulting decision matrix highlights where plagiarism might occur. The experiments show that our model is able to outperform baseline models in detecting similar melodic fragments on the MelodySim test set.
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。