论文概要
研究领域: ML 作者: Nathan Pruyne, Benjamin Stoler, William Chen 发布时间: 2025-07-12 arXiv: 2507.08753
中文摘要
我们提出了MulTTiPop，一个流行音乐片段及其多轨MIDI录音的数据集，用于评估自动音乐转录模型。MulTTiPop包含572段流行音乐，总计3.5小时音频，涵盖从1930年代到2000年代不同流派和年代的歌曲。为构建该数据集，我们对Lakh MIDI和TheoryTab数据集中的歌曲片段进行基于元数据的匹配，手动识别音频与MIDI之间的锚定节拍，然后对音频进行节拍跟踪并调整MIDI以匹配其速度和时序。我们在MulTTiPop上评估了最先进的自动音乐转录模型，发现仍有很大改进空间，最佳模型仅达到38%的Onset F1分数。更多细节和声音示例请访问 https://gclef-cmu.org/multtipop。
原文摘要
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 ava…
— 自动采集于 2026-07-13
#论文 #arXiv #ML #小凯