A Mamba-Based Model for Automatic Chord Recognition

TL;DR

This paper introduces BMACE, a bidirectional Mamba-based model that effectively captures temporal dependencies for automatic chord recognition, achieving high accuracy with fewer parameters and less computation.

Contribution

The paper presents a novel Mamba-based model for chord recognition that improves efficiency while maintaining high prediction performance.

Findings

Achieves comparable accuracy to state-of-the-art models

Uses fewer parameters and less computational resources

Effective modeling of temporal dependencies

Abstract

In this work, we propose a new efficient solution, which is a Mamba-based model named BMACE (Bidirectional Mamba-based network, for Automatic Chord Estimation), which utilizes selective structured state-space models in a bidirectional Mamba layer to effectively model temporal dependencies. Our model achieves high prediction performance comparable to state-of-the-art models, with the advantage of requiring fewer parameters and lower computational resources