# SignalTrain: Profiling Audio Compressors with Deep Neural Networks

**Authors:** Scott H. Hawley, Benjamin Colburn, Stylianos I. Mimilakis  
**arXiv:** [1905.11928](https://arxiv.org/abs/1905.11928)  
**Date:** 2019-05-28  
**Summary page:** https://www.summarizepaper.com/en/paper/1905.11928v1/

## Key points

- Study titled "SignalTrain: Profiling Audio Compressors with Deep Neural Networks"
- Data-driven approach for predicting behavior of non-linear audio signal processing effects
- Focus on audio compressors, developing mapping function using time-domain samples as input
- Utilization of deep auto-encoder model considering time-domain samples and control parameters
- Chosen effects are dynamic range compression audio effects (software-based and analog)
- Challenges posed by parameterized nonlinear time-dependent nature of compressors
- Experimental procedures capturing primary functional and auditory characteristics of compressors
- Noticeable audible noise present in processed audio signals despite promising results
- Further investigation and refinement needed before implementing profiling methods in real-world workflows
- Potential of deep neural networks for profiling audio effects highlighted, emphasizing need to address challenges for accurate practical applications

## Summary

In the study titled "SignalTrain: Profiling Audio Compressors with Deep Neural Networks," authors Scott H. Hawley, Benjamin Colburn, and Stylianos I. Mimilakis present a data-driven approach for predicting the behavior of non-linear audio signal processing effects. Their focus is specifically on audio compressors and their objective is to develop a mapping function that accurately predicts how an unprocessed audio signal will be affected by a given effect using time-domain samples as input. To achieve this goal, they utilize a deep auto-encoder model that takes into account both the time-domain samples and control parameters of the target effect. The chosen effects are dynamic range compression audio effects - including both software-based and analog compressors - due to their widespread use and complex nonlinear characteristics. These types of compressors pose challenges for profiling "general" audio effects because of their parameterized nonlinear time-dependent nature. Through experimental procedures, the researchers were able to capture the primary functional and auditory characteristics of the compressors using their proposed method. However, despite promising results in capturing key features of the compressors, there was still noticeable audible noise present in the processed audio signals. This indicates that further investigation and refinement are necessary before implementing such profiling methods in real-world audio processing workflows. Overall, this study highlights the potential of deep neural networks for profiling audio effects but also underscores the importance of addressing remaining challenges to ensure accurate and high-quality results in practical applications.