A Fully Convolutional Deep Auditory Model for Musical Chord Recognition

TL;DR

This paper introduces a fully convolutional deep auditory model for musical chord recognition that automatically learns features and achieves competitive or superior results compared to existing methods.

Contribution

The paper presents a novel end-to-end deep learning approach combining a convolutional auditory model with a CRF for improved chord recognition without manual feature engineering.

Findings

Learned features are musically interpretable

Achieves state-of-the-art or better accuracy

Automatically trains feature extraction and decoding stages

Abstract

Chord recognition systems depend on robust feature extraction pipelines. While these pipelines are traditionally hand-crafted, recent advances in end-to-end machine learning have begun to inspire researchers to explore data-driven methods for such tasks. In this paper, we present a chord recognition system that uses a fully convolutional deep auditory model for feature extraction. The extracted features are processed by a Conditional Random Field that decodes the final chord sequence. Both processing stages are trained automatically and do not require expert knowledge for optimising parameters. We show that the learned auditory system extracts musically interpretable features, and that the proposed chord recognition system achieves results on par or better than state-of-the-art algorithms.