# Investigation of Time-Frequency Feature Combinations with Histogram Layer Time Delay Neural Networks

arXiv: https://arxiv.org/abs/2409.13881 · HTML: https://mlsanity.com/paper/2409.13881/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 36 references that are in the map.
- First posted on arXiv 20 Sep 2024.

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

- [Deep Learning for Audio Signal Processing](https://mlsanity.com/paper/1905.00078/) (2019)
- [Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2305.03944/) (2023)
- [Histogram Layers for Texture Analysis](https://mlsanity.com/paper/2001.00215/) (2020)
- [Histogram Layer Time Delay Neural Networks for Passive Sonar Classification](https://mlsanity.com/paper/2307.13788/) (2023)
- [Possibilistic Fuzzy Local Information C-Means with Automated Feature Selection for Seafloor Segmentation](https://mlsanity.com/paper/2110.07433/) (2021)

## Abstract (arXiv)

While deep learning has reduced the prevalence of manual feature extraction, transformation of data via feature engineering remains essential for improving model performance, particularly for underwater acoustic signals. The methods by which audio signals are converted into time-frequency representations and the subsequent handling of these spectrograms can significantly impact performance. This work demonstrates the performance impact of using different combinations of time-frequency features in a histogram layer time delay neural network. An optimal set of features is identified with results indicating that specific feature combinations outperform single data features.