# Interpreting deep urban sound classification using Layer-wise Relevance Propagation

arXiv: https://arxiv.org/abs/2111.10235 · HTML: https://mlsanity.com/paper/2111.10235/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 19 Nov 2021.

## Builds on (most cited first, 8 of 8)

- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Deep Learning for Audio Signal Processing](https://mlsanity.com/paper/1905.00078/) (2019)
- [Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification](https://mlsanity.com/paper/1608.04363/) (2016)
- [AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark](https://mlsanity.com/paper/1807.03418/) (2018)
- [iNNvestigate neural networks!](https://mlsanity.com/paper/1808.04260/) (2018)
- [Adam revisited: a weighted past gradients perspective](https://mlsanity.com/paper/2101.00238/) (2021)
- [Neural Architecture Search on Acoustic Scene Classification](https://mlsanity.com/paper/1912.12825/) (2019)

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

- [Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features](https://mlsanity.com/paper/2309.07733/) (2023)
- [XAI-based Comparison of Input Representations for Audio Event Classification](https://mlsanity.com/paper/2304.14019/) (2023)

## Abstract (arXiv)

After constructing a deep neural network for urban sound classification, this work focuses on the sensitive application of assisting drivers suffering from hearing loss. As such, clear etiology justifying and interpreting model predictions comprise a strong requirement. To this end, we used two different representations of audio signals, i.e. Mel and constant-Q spectrograms, while the decisions made by the deep neural network are explained via layer-wise relevance propagation. At the same time, frequency content assigned with high relevance in both feature sets, indicates extremely discriminative information characterizing the present classification task. Overall, we present an explainable AI framework for understanding deep urban sound classification.