RECORD
Automatic Equalization for Individual Instrument Tracks Using Convolutional Neural Networks
Audio and Speech Processing · Submitted 23 Jul 2024
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We perform listening tests, and demonstrate that our proposed automatic equalization solution subjectively enhances the tonal characteristics for recordings of common instrument types.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
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.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | We propose a novel approach for the automatic equalization of individual musical instrument tracks. | contribution 1.00 | 0.87 | 0.09 | asserted 0.97 |
| s1 | Our method begins by identifying the instrument present within a source recording in order to choose its corresponding ideal spectrum as a target. | method 1.00 | 0.80 | 0.03 | asserted 0.99 |
| s2 | 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. | method 1.00 | 0.83 | 0.04 | asserted 0.99 |
| s3 | To this end, we build upon a differentiable parametric equalizer matching neural network, demonstrating improvements relative to previously established state-of-the-art. | contribution 0.43 | 0.85 | 0.14 | asserted 1.00 |
| s4 | 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. | contribution 0.83 | 0.93 | 0.11 | asserted 1.00 |
| s5 | 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. | result 1.00 | 0.96 | 0.32 | asserted 1.00 |
| s6 | We perform listening tests, and demonstrate that our proposed automatic equalization solution subjectively enhances the tonal characteristics for recordings of common instrument types. | result 0.98 | 0.97 | 0.35 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original 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.
Human review
References
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.