arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.03569cs.SDeess.ASeess.SP
收藏

基于Scalograms的深度Single Shot乐器识别

Deep Single Shot Musical Instrument Identification using Scalograms

National Institute of Technology, Durgapur(杜尔加布尔国家理工学院);Indian Institute of Science(印度科学学院);Steradian Semiconductors Pvt. Ltd.(斯特拉迪安半导体私人有限公司)

Debdutta Chatterjee, Arindam Dutta, Dibakar Sil, Aniruddha Chandra

摘要:

乐器识别一直被认为是音乐信息检索领域中最难解决的问题之一。尽管有几次强有力的尝试来解决这个问题,一个跨越过去五十多年的时间轴,这个问题仍然是一个悬而未决的难题。在这项工作中,作者采取了传统问题陈述的进一步复杂版本。他们试图用最少的可用数据来解决这个问题--每节课一段音频摘录。我们建议使用卷积暹罗网络和相同的残差变体来基于其音频摘录的相应尺度图识别乐器。我们的实验和相应的结果在两个公开可用的数据集上验证了我们的算法的优越性$\approx$ 3\%比现有的同义算法在当今的文献。

英文摘要:

Musical Instrument Identification has for long had a reputation of being one of the most ill-posed problems in the field of Musical Information Retrieval(MIR). Despite several robust attempts to solve the problem, a timeline spanning over the last five odd decades, the problem remains an open conundrum. In this work, the authors take on a further complex version of the traditional problem statement. They attempt to solve the problem with minimal data available - one audio excerpt per class. We propose to use a convolutional Siamese network and a residual variant of the same to identify musical instruments based on the corresponding scalograms of their audio excerpts. Our experiments and corresponding results obtained on two publicly available datasets validate the superiority of our algorithm by $\approx$ 3\% over the existing synonymous algorithms in present-day literature.

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。

↑