arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.07428cs.SDcs.LGcs.MMeess.AS
收藏

只需标注反复记号:针对真实场景音频到乐谱对齐

Just Label the Repeats for In-The-Wild Audio-to-Score Alignment

Carnegie Mellon University(卡内基梅隆大学)

Irmak Bukey, Michael Feffer, Chris Donahue

AI总结:

提出一种高效的真实场景音频到乐谱对齐工作流程,通过用户快速标注反复记号、改进特征表示及评估协议,将对齐精度从33%提升至82%。

摘要:

我们提出了一种高效的工作流程,用于实现真实场景演奏音频与对应乐谱扫描件(图像)的高质量离线对齐。近期关于音频到乐谱对齐的工作扩展了动态时间规整(DTW),使其在理论上能够处理由反复记号引起的乐谱跳转——该方法无需人工标注,但我们表明它通常会产生低质量的对齐结果。作为替代方案,我们提出了一种工作流程和界面,允许用户快速标注跳转(通过点击反复记号),这需要少量人工监督,但平均而言能产生质量高得多的对齐结果。此外,我们改进了音频和乐谱特征表示以提高对齐质量,具体方式为:(1)将小节检测集成到乐谱特征表示中,以及(2)使用来自音乐转录模型的原始起音预测概率代替钢琴卷帘。我们提出了一种音频到乐谱对齐的评估协议,以小节为单位计算估计对齐与真实对齐之间的距离。在此评估下,我们发现我们提出的跳转标注工作流程和改进的特征表示共同将对齐精度提高了150%(相对于先前工作的33%提升至82%)。

英文摘要:

We propose an efficient workflow for high-quality offline alignment of in-the-wild performance audio and corresponding sheet music scans (images). Recent work on audio-to-score alignment extends dynamic time warping (DTW) to be theoretically able to handle jumps in sheet music induced by repeat signs-this method requires no human annotations, but we show that it often yields low-quality alignments. As an alternative, we propose a workflow and interface that allows users to quickly annotate jumps (by clicking on repeat signs), requiring a small amount of human supervision but yielding much higher quality alignments on average. Additionally, we refine audio and score feature representations to improve alignment quality by: (1) integrating measure detection into the score feature representation, and (2) using raw onset prediction probabilities from a music transcription model instead of piano roll. We propose an evaluation protocol for audio-to-score alignment that computes the distance between the estimated and ground truth alignment in units of measures. Under this evaluation, we find that our proposed jump annotation workflow and improved feature representations together improve alignment accuracy by 150% relative to prior work (33% to 82%).

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。

↑