用合成加转录联合训练，仅凭乐谱标注就能分离鼓组音轨。
The Inverse Drum Machine: Source Separation Through Joint Transcription and Analysis-by-Synthesis
- 通过音符时间+样本合成的闭环框架，端到端优化分离与转录。
- 在StemGMD数据集上达到与需独立音轨训练的方法相当的分离效果。
- 适合无独立音轨标注但有乐谱信息的音乐信号处理任务。
我们提出逆向鼓机（Inverse Drum Machine, IDM），一种新型鼓组源分离方法，结合分析-合成框架与深度学习。不同于近期需要孤立音轨训练的监督方法，IDM仅需鼓混合音轨与转录标注即可训练。IDM融合自动鼓乐转录与单次鼓采样合成，以端到端方式联合优化。通过将合成的单次采样与估计的击打时间进行卷积，模拟鼓机生成过程，重建各鼓组音轨，并在此基础上训练深度神经网络。在StemGMD数据集上的实验表明，IDM的分离质量可媲美需独立音轨数据的最先进监督方法。
原文摘要 · Abstract (English)
We present the Inverse Drum Machine, a novel approach to Drum Source Separation that leverages an analysis-by-synthesis framework combined with deep learning. Unlike recent supervised methods that require isolated stem recordings for training, our approach is trained on drum mixtures with only transcription annotations. IDM integrates Automatic Drum Transcription and One-shot Drum Sample Synthesis, jointly optimizing these tasks in an end-to-end manner. By convolving synthesized one-shot samples with estimated onsets, akin to a drum machine, we reconstruct the individual drum stems and train a Deep Neural Network on the reconstruction of the mixture. Experiments on the StemGMD dataset demonstrate that IDM achieves separation quality comparable to state-of-the-art supervised methods that require isolated stems data.
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。