# Deep Active Audio Feature Learning in Resource-Constrained Environments

arXiv: https://arxiv.org/abs/2308.13201 · HTML: https://mlsanity.com/paper/2308.13201/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 75 references that are in the map.
- First posted on arXiv 25 Aug 2023.

## Builds on (most cited first, 13 of 13)

- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Should we really use post-hoc tests based on mean-ranks?](https://mlsanity.com/paper/1505.02288/) (2015)
- [Learning from Between-class Examples for Deep Sound Recognition](https://mlsanity.com/paper/1711.10282/) (2017)
- [Knowledge Distillation for Improved Accuracy in Spoken Question Answering](https://mlsanity.com/paper/2010.11067/) (2020)
- [Large-scale weakly supervised audio classification using gated convolutional neural network](https://mlsanity.com/paper/1710.00343/) (2017)
- [Active Learning for Sound Event Detection](https://mlsanity.com/paper/2002.05033/) (2020)
- [Flying Insect Classification with Inexpensive Sensors](https://mlsanity.com/paper/1403.2654/) (2014)
- [AclNet: efficient end-to-end audio classification CNN](https://mlsanity.com/paper/1811.06669/) (2018)
- [Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices](https://mlsanity.com/paper/2103.03483/) (2021)
- [Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices](https://mlsanity.com/paper/2108.06128/) (2021)

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

- [Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables](https://mlsanity.com/paper/2502.09073/) (2025)
- [Hybrid Disagreement-Diversity Active Learning for Bioacoustic Sound Event Detection](https://mlsanity.com/paper/2505.20956/) (2025)
- [Active Learning for Biodiversity Monitoring: From Label Efficiency to Reliable Ecological Inference](https://mlsanity.com/paper/2609.27409/) (2026)

## Abstract (arXiv)

The scarcity of labelled data makes training Deep Neural Network (DNN) models in bioacoustic applications challenging. In typical bioacoustics applications, manually labelling the required amount of data can be prohibitively expensive. To effectively identify both new and current classes, DNN models must continue to learn new features from a modest amount of fresh data. Active Learning (AL) is an approach that can help with this learning while requiring little labelling effort. Nevertheless, the use of fixed feature extraction approaches limits feature quality, resulting in underutilization of the benefits of AL. We describe an AL framework that addresses this issue by incorporating feature extraction into the AL loop and refining the feature extractor after each round of manual annotation. In addition, we use raw audio processing rather than spectrograms, which is a novel approach. Experiments reveal that the proposed AL framework requires 14.3%, 66.7%, and 47.4% less labelling effort on benchmark audio datasets ESC-50, UrbanSound8k, and InsectWingBeat, respectively, for a large DNN model and similar savings on a microcontroller-based counterpart. Furthermore, we showcase the practical relevance of our study by incorporating data from conservation biology projects. All codes are publicly available on GitHub.