Automatic Equalization for Individual Instrument Tracks Using Convolutional Neural Networks

TL;DR

This paper introduces a neural network-based system for automatic equalization of individual instrument tracks, which identifies instruments, predicts ideal spectra, and fine-tunes equalizer settings, improving sound quality in real-world recordings.

Contribution

The authors develop a differentiable neural network for parametric equalizer matching that leverages real-world data during training, enhancing accuracy over previous methods.

Findings

Reduces mean absolute error by 24% in equalizer matching

Subjectively improves tonal quality of instrument recordings

Enables automated training data generation for real-world scenarios

Abstract

We propose a novel approach for the automatic equalization of individual musical instrument tracks. Our method begins by identifying the instrument present within a source recording in order to choose its corresponding ideal spectrum as a target. Next, the spectral difference between the recording and the target is calculated, and accordingly, an equalizer matching model is used to predict settings for a parametric equalizer. To this end, we build upon a differentiable parametric equalizer matching neural network, demonstrating improvements relative to previously established state-of-the-art. Unlike past approaches, we show how our system naturally allows real-world audio data to be leveraged during the training of our matching model, effectively generating suitably produced training targets in an automated manner mirroring conditions at inference time. Consequently, we illustrate how fine-tuning our matching model on such examples considerably improves parametric equalizer matching performance in real-world scenarios, decreasing mean absolute error by 24% relative to methods relying solely on random parameter sampling techniques as a self-supervised learning strategy. We perform listening tests, and demonstrate that our proposed automatic equalization solution subjectively enhances the tonal characteristics for recordings of common instrument types.