MulTTiPop：一个用于流行音乐的多轨转录数据集 / MulTTiPop: A Multitrack Transcription Dataset for Pop Music
1️⃣ 一句话总结
本文提出了MulTTiPop数据集，包含572段、总计3.5小时的流行音乐片段及其对应的多轨MIDI文件，覆盖1930年代至2000年代的多种风格，用于评估自动音乐转录模型，实验显示现有最佳模型仅达到38%的起始点F1分数，表明了该领域仍有很大的改进空间。
arXiv 提交日期: 2026-07-09
Abstract - MulTTiPop: A Multitrack Transcription Dataset for Pop Music
We present MulTTiPop, a dataset of pop music segments and their associated multitrack MIDI recordings for the evaluation of automatic music transcription models. MulTTiPop contains 572 segments of popular music totaling 3.5 hours of audio, and contains songs from diverse genres and decades from the 1930s to 2000s. To collect this dataset, we perform metadata-based matching on song segments from the Lakh MIDI and TheoryTab datasets, manually identify an anchor beat between the audio and MIDI, then use beat tracking on the audio and warp the MIDI to match its tempo and timing. We evaluate state-of-the-art automatic music transcription models on MulTTiPop and find substantial room for improvement, with the best model achieving 38% Onset F1. More details and sound examples of MulTTiPop are available at this https URL.
源自 arXiv: 2607.08756