# Comparative Study of State-based Neural Networks for Virtual Analog Audio Effects Modeling

arXiv: https://arxiv.org/abs/2405.04124 · HTML: https://mlsanity.com/paper/2405.04124/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 55 references that are in the map.
- First posted on arXiv 7 May 2024.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [HiPPO: Recurrent Memory with Optimal Polynomial Projections](https://mlsanity.com/paper/2008.07669/) (2020)
- [On the Parameterization and Initialization of Diagonal State Space Models](https://mlsanity.com/paper/2206.11893/) (2022)
- [Resurrecting Recurrent Neural Networks for Long Sequences](https://mlsanity.com/paper/2303.06349/) (2023)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [Deep Learning for Tube Amplifier Emulation](https://mlsanity.com/paper/1811.00334/) (2018)
- [Identification of block-oriented nonlinear systems starting from linear approximations: A survey](https://mlsanity.com/paper/1607.01217/) (2016)
- [Modelling black-box audio effects with time-varying feature modulation](https://mlsanity.com/paper/2211.00497/) (2022)
- [Lightweight and interpretable neural modeling of an audio distortion effect using hyperconditioned differentiable biquads](https://mlsanity.com/paper/2103.08709/) (2021)
- [Modeling of nonlinear audio effects with end-to-end deep neural networks](https://mlsanity.com/paper/1810.06603/) (2018)
- [Modeling plate and spring reverberation using a DSP-informed deep neural network](https://mlsanity.com/paper/1910.10105/) (2019)
- [Neural modeling of magnetic tape recorders](https://mlsanity.com/paper/2305.16862/) (2023)
- [A Comparison of Virtual Analog Modelling Techniques for Desktop and Embedded Implementations](https://mlsanity.com/paper/2009.02833/) (2020)
- [Virtual Analog Modeling of Distortion Circuits Using Neural Ordinary Differential Equations](https://mlsanity.com/paper/2205.01897/) (2022)

## Built on by (most cited first, 3 of 3)

- [Unsupervised Estimation of Nonlinear Audio Effects: Comparing Diffusion-Based and Adversarial approaches](https://mlsanity.com/paper/2504.04751/) (2025)
- [Modeling Time-Dependent Responses of Optical Compressors with Selective State Space Models](https://mlsanity.com/paper/2408.12549/) (2024)
- [A Simple State Space Model Excels at Multivariate Time Series Classification](https://mlsanity.com/paper/2605.27406/) (2026)

## Abstract (arXiv)

Artificial neural networks are a promising technique for virtual analog modeling, having shown particular success in emulating distortion circuits. Despite their potential, enhancements are needed to enable effect parameters to influence the network's response and to achieve a low-latency output. While hybrid solutions, which incorporate both analytical and black-box techniques, offer certain advantages, black-box approaches, such as neural networks, can be preferable in contexts where rapid deployment, simplicity, or adaptability are required, and where understanding the internal mechanisms of the system is less critical. In this article, we explore the application of recent machine learning advancements for virtual analog modeling. We compare State-Space models and Linear Recurrent Units against the more common LSTM networks, with a variety of audio effects. We evaluate the performance and limitations of these models using multiple metrics, providing insights for future research and development. Our metrics aim to assess the models' ability to accurately replicate the signal's energy and frequency contents, with a particular focus on transients. The Feature-wise Linear Modulation method is employed to incorporate effect parameters that influence the network's response, enabling dynamic adaptability based on specified conditions. Experimental results suggest that LSTM networks offer an advantage in emulating distortions and equalizers, although performance differences are sometimes subtle yet statistically significant. On the other hand, encoder-decoder configurations of Long Short-Term Memory networks and State-Space models excel in modeling saturation and compression, effectively managing the dynamic aspects inherent in these effects. However, no models effectively emulate the low-pass filter, and Linear Recurrent Units show inconsistent performance across various audio effects.