# A Feature Learning Siamese Model for Intelligent Control of the Dynamic Range Compressor

arXiv: https://arxiv.org/abs/1905.01022 · HTML: https://mlsanity.com/paper/1905.01022/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2019.

## Built on by (most cited first, 7 of 7)

- [Differentiable Signal Processing With Black-Box Audio Effects](https://mlsanity.com/paper/2105.04752/) (2021)
- [Modulation Extraction for LFO-driven Audio Effects](https://mlsanity.com/paper/2305.13262/) (2023)
- [Adoption of AI Technology in the Music Mixing Workflow: An Investigation](https://mlsanity.com/paper/2304.03407/) (2023)
- [SerumRNN: Step by Step Audio VST Effect Programming](https://mlsanity.com/paper/2104.03876/) (2021)
- [Discrete-time Contraction-based Control of Nonlinear Systems with Parametric Uncertainties using Neural Networks](https://mlsanity.com/paper/2105.05432/) (2021)
- [White-box Audio VST Effect Programming](https://mlsanity.com/paper/2102.03170/) (2021)
- [Style Transfer for Non-differentiable Audio Effects](https://mlsanity.com/paper/2309.17125/) (2023)

## Abstract (arXiv)

In this paper, a siamese DNN model is proposed to learn the characteristics of the audio dynamic range compressor (DRC). This facilitates an intelligent control system that uses audio examples to configure the DRC, a widely used non-linear audio signal conditioning technique in the areas of music production, speech communication and broadcasting. Several alternative siamese DNN architectures are proposed to learn feature embeddings that can characterise subtle effects due to dynamic range compression. These models are compared with each other as well as handcrafted features proposed in previous work. The evaluation of the relations between the hyperparameters of DNN and DRC parameters are also provided. The best model is able to produce a universal feature embedding that is capable of predicting multiple DRC parameters simultaneously, which is a significant improvement from our previous research. The feature embedding shows better performance than handcrafted audio features when predicting DRC parameters for both mono-instrument audio loops and polyphonic music pieces.