# TB or not TB? Acoustic cough analysis for tuberculosis classification

arXiv: https://arxiv.org/abs/2209.00934 · HTML: https://mlsanity.com/paper/2209.00934/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 2 Sep 2022.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [Streaming keyword spotting on mobile devices](https://mlsanity.com/paper/2005.06720/) (2020)
- [A neural attention model for speech command recognition](https://mlsanity.com/paper/1808.08929/) (2018)
- [COVID-19 Cough Classification using Machine Learning and Global Smartphone Recordings](https://mlsanity.com/paper/2012.01926/) (2020)
- [Cough Against COVID: Evidence of COVID-19 Signature in Cough Sounds](https://mlsanity.com/paper/2009.08790/) (2020)
- [Automatic Cough Classification for Tuberculosis Screening in a Real-World Environment](https://mlsanity.com/paper/2103.13300/) (2021)
- [Speaker Recognition with Cough, Laugh and "Wei"](https://mlsanity.com/paper/1706.07860/) (2017)

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

- [Predicting Tuberculosis from Real-World Cough Audio Recordings and Metadata](https://mlsanity.com/paper/2307.04842/) (2023)
- [Tuberculosis Screening from Cough Audio: Baseline Models, Clinical Variables, and Uncertainty Quantification](https://mlsanity.com/paper/2601.07969/) (2026)
- [Cough activity detection for automatic tuberculosis screening](https://mlsanity.com/paper/2603.11241/) (2026)

## Abstract (arXiv)

In this work, we explore recurrent neural network architectures for tuberculosis (TB) cough classification. In contrast to previous unsuccessful attempts to implement deep architectures in this domain, we show that a basic bidirectional long short-term memory network (BiLSTM) can achieve improved performance. In addition, we show that by performing greedy feature selection in conjunction with a newly-proposed attention-based architecture that learns patient invariant features, substantially better generalisation can be achieved compared to a baseline and other considered architectures. Furthermore, this attention mechanism allows an inspection of the temporal regions of the audio signal considered to be important for classification to be performed. Finally, we develop a neural style transfer technique to infer idealised inputs which can subsequently be analysed. We find distinct differences between the idealised power spectra of TB and non-TB coughs, which provide clues about the origin of the features in the audio signal.