Disentangled Multidimensional Metric Learning For Music Similarity

Abstract

Music similarity search is useful for a variety of creative tasks such as replacing one music recording with another recording with a similar "feel", a common task in video editing. For this task, it is typically necessary to define a similarity metric to compare one recording to another. Music similarity, however, is hard to define and depends on multiple simultaneous notions of similarity (i.e. genre, mood, instrument, tempo). While prior work ignore this issue, we embrace this idea and introduce the concept of multidimensional similarity and unify both global and specialized similarity metrics into a single, semantically disentangled multidimensional similarity metric. To do so, we adapt a variant of deep metric learning called conditional similarity networks to the audio domain and extend it using track-based information to control the specificity of our model. We evaluate our method and show that our single, multidimensional model outperforms both specialized similarity spaces and

Stats

• citations25
• S2 citations—
• github stars0
• HF likes0
• heat score10.61
• arxiv keylee2020disentangled

Related papers

• Metric Learning Vs Classification For Disentangled Music Representation Learning (2020)0.00
• Multimodal Metric Learning For Tag-based Music Retrieval (2020)9.76
• Self-supervised Auxiliary Loss For Metric Learning In Music Similarity-based Retrieval And Auto-tagging (2023)0.00
• Musical Audio Similarity With Self-supervised Convolutional Neural Networks (2022)0.00
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Anchor-aware Deep Metric Learning For Audio-visual Retrieval (2024)6.34
• Contrastive Learning For Cross-modal Artist Retrieval (2023)0.00
• Metric Learning By Similarity Network For Deep Semi-supervised Learning (2020)3.58