# A Mamba-Based Model for Automatic Chord Recognition

Source: [A Mamba-Based Model for Automatic Chord Recognition](<https://www.sota2.com/research/paper/695c970253fdd5c3617436ed>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-07T05:00:11.096Z

Authors: Chunyu Yuan, Johanna Devaney

Published: 2026-01-05T13:27:42.000Z

## 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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Chord Recognition on uspop2002 25-label maj-min vocabulary (val)](<https://www.sota2.com/research/sota/chord-recognition-on-uspop2002-25-label-maj-min-vocabulary-val.md>): Chord Recognition; uspop2002 25-label maj-min vocabulary (val); Root Accuracy: 82.12.

- [Chord Recognition on uspop2002 170-label large vocabulary (val)](<https://www.sota2.com/research/sota/chord-recognition-on-uspop2002-170-label-large-vocabulary-val.md>): Chord Recognition; uspop2002 170-label large vocabulary (val); Root: 80.43.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2601.02101>)

[PDF](<https://arxiv.org/pdf/2601.02101.pdf>)