arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.08653cs.SDeess.AS
收藏

GAPS:一个大型且多样的古典吉他数据集与基准转录模型

GAPS: A Large and Diverse Classical Guitar Dataset and Benchmark Transcription Model

Queen Mary University of London(伦敦玛丽女王大学)

Xavier Riley, Zixun Guo, Drew Edwards, Simon Dixon

AI总结:

本文提出最大的古典吉他音频-乐谱对齐数据集 GAPS,并基于其训练出在 GuitarSet 上有监督和零样本设置下均达最先进水平的吉他自动转录模型。

摘要:

我们介绍 GAPS(Guitar-Aligned Performance Scores,吉他对齐演奏乐谱),这是一个新的古典吉他演奏数据集,以及一个基准吉他转录模型,该模型在 GuitarSet 上于有监督和零样本两种设置下均取得了最先进的性能。GAPS 是最大的真实吉他音频数据集,包含 14 小时可自由获取的音频-乐谱对齐数据,由 200 多位演奏者在多样化条件下录制,并配有高分辨率音符级 MIDI 对齐和演奏视频。这些数据使我们能够训练一个用于独奏吉他录音自动转录的最先进模型,该模型能够很好地泛化到训练期间未见过的真实世界音频。

英文摘要:

We introduce GAPS (Guitar-Aligned Performance Scores), a new dataset of classical guitar performances, and a benchmark guitar transcription model that achieves state-of-the-art performance on GuitarSet in both supervised and zero-shot settings. GAPS is the largest dataset of real guitar audio, containing 14 hours of freely available audio-score aligned pairs, recorded in diverse conditions by over 200 performers, together with high-resolution note-level MIDI alignments and performance videos. These enable us to train a state-of-the-art model for automatic transcription of solo guitar recordings which can generalise well to real world audio that is unseen during training.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑