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.

翻译：音频嵌入技术能够实现音频文件的大规模相似度比较，广泛应用于搜索与推荐系统。由于音频相似性具有主观性特征，设计系统时不仅需要判断音频是否相似，更需要明确其相似维度（例如节奏、情绪或风格）。已有研究提出解耦嵌入空间，通过对表示特定属性（可能相互关联）的子空间进行加权，可在下游任务中突出这些属性。然而，目前尚未有研究探讨这些子空间的独立性及其操控方法，以检索那些“相似但特定维度不同”的曲目。本文以节拍操控为案例，探索嵌入空间中节拍属性的调控方法。我们提出节拍迁移函数，该函数能在保持音乐类型等其他属性的前提下，对预训练嵌入空间中的节拍进行高效调控。由于该迁移函数专为节拍设计，因此能够实现“相似但节拍不同”的曲目检索。实验表明，该函数可作为高效数据增强策略，不仅用于训练下游节拍预测模型，还能优化与节拍弱相关属性的最近邻检索性能。