Learning Normal Patterns in Musical Loops
This research provides a flexible, fully unsupervised solution for music information retrieval, addressing challenges such as reliance on handcrafted features and domain-specific limitations, though it is incremental as it builds on existing deep learning and anomaly detection techniques.
The paper tackles the problem of detecting audio patterns in musical loops using an unsupervised anomaly detection framework, achieving improved anomaly separation, especially for larger variations, with results showing the residual autoencoder variant outperforming baselines like Isolation Forest and PCA methods.
This paper introduces an unsupervised framework for detecting audio patterns in musical samples (loops) through anomaly detection techniques, addressing challenges in music information retrieval (MIR). Existing methods are often constrained by reliance on handcrafted features, domain-specific limitations, or dependence on iterative user interaction. We address these limitations through an architecture combining deep feature extraction with unsupervised anomaly detection. Our approach leverages a pre-trained Hierarchical Token-semantic Audio Transformer (HTS-AT), paired with a Feature Fusion Mechanism (FFM), to generate representations from variable-length audio loops. These embeddings are processed using one-class Deep Support Vector Data Description (Deep SVDD), which learns normative audio patterns by mapping them to a compact latent hypersphere. Evaluations on curated bass and guitar datasets compare standard and residual autoencoder variants against baselines like Isolation Forest (IF) and and principle component analysis (PCA) methods. Results show our Deep SVDD models, especially the residual autoencoder variant, deliver improved anomaly separation, particularly for larger variations. This research contributes a flexible, fully unsupervised solution for processing diverse audio samples, overcoming previous structural and input limitations while enabling effective pattern identification through distance-based latent space scoring.