# Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices

arXiv: https://arxiv.org/abs/2105.11856 · HTML: https://mlsanity.com/paper/2105.11856/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 31 references that are in the map.
- First posted on arXiv 25 May 2021.

## Builds on (most cited first, 5 of 5)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [A multi-device dataset for urban acoustic scene classification](https://mlsanity.com/paper/1807.09840/) (2018)
- [Trainable Frontend For Robust and Far-Field Keyword Spotting](https://mlsanity.com/paper/1607.05666/) (2016)
- [Unsupervised adversarial domain adaptation for acoustic scene classification](https://mlsanity.com/paper/1808.05777/) (2018)

## Built on by (most cited first, 2 of 2)

- [Deep Space Separable Distillation for Lightweight Acoustic Scene Classification](https://mlsanity.com/paper/2405.03567/) (2024)
- [Adversarial Training Improves Generalization Under Distribution Shifts in Bird Sound Classification](https://mlsanity.com/paper/2507.13727/) (2025)

## Abstract (arXiv)

Machine learning algorithms, when trained on audio recordings from a limited set of devices, may not generalize well to samples recorded using other devices with different frequency responses. In this work, a relatively straightforward method is introduced to address this problem. Two variants of the approach are presented. First requires aligned examples from multiple devices, the second approach alleviates this requirement. This method works for both time and frequency domain representations of audio recordings. Further, a relation to standardization and Cepstral Mean Subtraction is analysed. The proposed approach becomes effective even when very few examples are provided. This method was developed during the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge and won the 1st place in the scenario with mis-matched recording devices with the accuracy of 75%. Source code for the experiments can be found online.