arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.08902cs.SDcs.DLcs.IRcs.LGeess.AS
收藏

相似但更快:音乐音频嵌入中节奏的操控用于节奏预测与搜索

Similar but Faster: Manipulation of Tempo in Music Audio Embeddings for Tempo Prediction and Search

SiriusXM-Pandora

Matthew C. McCallum, Florian Henkel, Jaehun Kim, Samuel E. Sandberg, Matthew E. P. Davies

AI总结:

本文提出节奏平移函数,在保持流派等属性的同时高效操控音乐音频嵌入中的节奏,用于检索相似但节奏不同的音轨,并验证其可提升节奏预测训练和最近邻检索效果。

摘要:

音频嵌入使得对音频文件相似性的大规模比较成为可能,可应用于搜索和推荐等场景。由于音频相似性具有主观性,设计系统时可能不仅需要回答音频是否相似,还要回答在哪些方面相似(例如节奏、情绪或流派)。以往的工作提出了解耦的嵌入空间,其中表示特定但可能相关属性的子空间可以被加权,以便在下游任务中强调这些属性。然而,目前尚无研究探讨这些子空间的独立性,也没有研究如何操控这些子空间,以检索那些相似但在特定方面不同的音轨。在此,我们以嵌入空间中节奏的操控作为案例研究,朝着这一目标进行探索。我们提出了节奏平移函数,能够在已有的嵌入空间内高效地操控节奏,同时保持流派等其他属性。由于这种平移专门针对节奏,因此能够检索出相似但节奏明显不同的音轨。我们表明,这种函数可以作为一种高效的数据增强策略,既可用于训练下游节奏预测器,也可改善与节奏基本无关的属性的最近邻检索。

英文摘要:

Audio embeddings enable large scale comparisons of the similarity of audio files for applications such as search and recommendation. Due to the subjectivity of audio similarity, it can be desirable to design systems that answer not only whether audio is similar, but similar in what way (e.g., wrt. tempo, mood or genre). Previous works have proposed disentangled embedding spaces where subspaces representing specific, yet possibly correlated, attributes can be weighted to emphasize those attributes in downstream tasks. However, no research has been conducted into the independence of these subspaces, nor their manipulation, in order to retrieve tracks that are similar but different in a specific way. Here, we explore the manipulation of tempo in embedding spaces as a case-study towards this goal. We propose tempo translation functions that allow for efficient manipulation of tempo within a pre-existing embedding space whilst maintaining other properties such as genre. As this translation is specific to tempo it enables retrieval of tracks that are similar but have specifically different tempi. We show that such a function can be used as an efficient data augmentation strategy for both training of downstream tempo predictors, and improved nearest neighbor retrieval of properties largely independent of tempo.

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。

↑