# Deep Feature Embedding and Hierarchical Classification for Audio Scene Classification

arXiv: https://arxiv.org/abs/2002.04857 · HTML: https://mlsanity.com/paper/2002.04857/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2020.

## Built on by (most cited first, 6 of 6)

- [An Audio-Visual Dataset and Deep Learning Frameworks for Crowded Scene Classification](https://mlsanity.com/paper/2112.09172/) (2021)
- [Rank-based loss for learning hierarchical representations](https://mlsanity.com/paper/2110.05941/) (2021)
- [Low-complexity deep learning frameworks for acoustic scene classification](https://mlsanity.com/paper/2206.06057/) (2022)
- [Robust, General, and Low Complexity Acoustic Scene Classification Systems and An Effective Visualization for Presenting a Sound Scene Context](https://mlsanity.com/paper/2210.08610/) (2022)
- [An Unsupervised Machine Learning Approach for Ground-Motion Spectra Clustering and Selection](https://mlsanity.com/paper/2212.03188/) (2022)
- [Low-complexity deep learning frameworks for acoustic scene classification using teacher-student scheme and multiple spectrograms](https://mlsanity.com/paper/2305.09463/) (2023)

## Abstract (arXiv)

In this work, we propose an approach that features deep feature embedding learning and hierarchical classification with triplet loss function for Acoustic Scene Classification (ASC). In the one hand, a deep convolutional neural network is firstly trained to learn a feature embedding from scene audio signals. Via the trained convolutional neural network, the learned embedding embeds an input into the embedding feature space and transforms it into a high-level feature vector for representation. In the other hand, in order to exploit the structure of the scene categories, the original scene classification problem is structured into a hierarchy where similar categories are grouped into meta-categories. Then, hierarchical classification is accomplished using deep neural network classifiers associated with triplet loss function. Our experiments show that the proposed system achieves good performance on both the DCASE 2018 Task 1A and 1B datasets, resulting in accuracy gains of 15.6% and 16.6% absolute over the DCASE 2018 baseline on Task 1A and 1B, respectively.