arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.00188cs.SDcs.LG
收藏

利用扩展的Groove MIDI数据集提高磁鼓转录的感知质量

Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Dataset

Google(谷歌)

Lee Callender, Curtis Hawthorne, Jesse Engel

摘要:

我们介绍了扩展的凹槽录音数据集(E-GMD),这是一个自动鼓转录(ADT)数据集,包含来自43个鼓包的444小时音频,使其比类似数据集大一个数量级,并且是第一个具有人类执行速度注释的数据集。我们使用E-GMD来优化分类器,通过预测表达动态(速度)来优化下游生成,并通过听力测试显示,尽管分类指标的结果相似,但它们产生的输出具有更好的感知质量。通过听力测试,我们认为,标准的分类器指标,如准确性和F-测量分数,是不够的代理下游任务的性能,因为它们不完全符合所生成的输出的感知质量。

英文摘要:

We introduce the Expanded Groove MIDI dataset (E-GMD), an automatic drum transcription (ADT) dataset that contains 444 hours of audio from 43 drum kits, making it an order of magnitude larger than similar datasets, and the first with human-performed velocity annotations. We use E-GMD to optimize classifiers for use in downstream generation by predicting expressive dynamics (velocity) and show with listening tests that they produce outputs with improved perceptual quality, despite similar results on classification metrics. Via the listening tests, we argue that standard classifier metrics, such as accuracy and F-measure score, are insufficient proxies of performance in downstream tasks because they do not fully align with the perceptual quality of generated outputs.

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。

↑