Hyperbolic Embeddings for Order-Aware Classification of Audio Effect Chains

TL;DR

This paper introduces a neural network approach that embeds wet audio signals into hyperbolic space to accurately recognize and classify the order of audio effect chains, addressing a key gap in music production analysis.

Contribution

It proposes a novel hyperbolic embedding method for jointly estimating AFX types and their order from wet signals, leveraging tree-structured data representation.

Findings

Hyperbolic embeddings outperform Euclidean ones in AFX chain classification.

The method effectively captures the non-commutative nature of effect order.

Experiments show improved accuracy in recognizing effect chains from guitar sounds.

Abstract

Audio effects (AFXs) are essential tools in music production, frequently applied in chains to shape timbre and dynamics. The order of AFXs in a chain plays a crucial role in determining the final sound, particularly when non-linear (e.g., distortion) or time-variant (e.g., chorus) processors are involved. Despite its importance, most AFX-related studies have primarily focused on estimating effect types and their parameters from a wet signal. To address this gap, we formulate AFX chain recognition as the task of jointly estimating AFX types and their order from a wet signal. We propose a neural-network-based method that embeds wet signals into a hyperbolic space and classifies their AFX chains. Hyperbolic space can represent tree-structured data more efficiently than Euclidean space due to its exponential expansion property. Since AFX chains can be represented as trees, with AFXs as nodes and edges encoding effect order, hyperbolic space is well-suited for modeling the exponentially growing and non-commutative nature of ordered AFX combinations, where changes in effect order can result in different final sounds. Experiments using guitar sounds demonstrate that, with an appropriate curvature, the proposed method outperforms its Euclidean counterpart. Further analysis based on AFX type and chain length highlights the effectiveness of the proposed method in capturing AFX order.