# A Dual-Purpose Deep Learning Model for Auscultated Lung and Tracheal Sound Analysis Based on Mixed Set Training

arXiv: https://arxiv.org/abs/2107.04229 · HTML: https://mlsanity.com/paper/2107.04229/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 66 references that are in the map.
- First posted on arXiv 9 Jul 2021.

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

- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Deep Learning Scaling is Predictable, Empirically](https://mlsanity.com/paper/1712.00409/) (2017)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database-HF_Lung_V1](https://mlsanity.com/paper/2102.03049/) (2021)
- [Deep Neural Network for Respiratory Sound Classification in Wearable Devices Enabled by Patient Specific Model Tuning](https://mlsanity.com/paper/2004.08287/) (2020)
- [Convolutional neural network for breathing phase detection in lung sounds](https://mlsanity.com/paper/1903.10251/) (2019)
- [Development of a Respiratory Sound Labeling Software for Training a Deep Learning-Based Respiratory Sound Analysis Model](https://mlsanity.com/paper/2101.01352/) (2021)
- [An Update on a Progressively Expanded Database for Automated Lung Sound Analysis](https://mlsanity.com/paper/2102.04062/) (2021)

## Built on by (most cited first, 1 of 1)

- [EZhouNet:A framework based on graph neural network and anchor interval for the respiratory sound event detection](https://mlsanity.com/paper/2509.01153/) (2025)

## Abstract (arXiv)

Many deep learning-based computerized respiratory sound analysis methods have previously been developed. However, these studies focus on either lung sound only or tracheal sound only. The effectiveness of using a lung sound analysis algorithm on tracheal sound and vice versa has never been investigated. Furthermore, no one knows whether using lung and tracheal sounds together in training a respiratory sound analysis model is beneficial. In this study, we first constructed a tracheal sound database, HF_Tracheal_V1, containing 10448 15-s tracheal sound recordings, 21741 inhalation labels, 15858 exhalation labels, and 6414 continuous adventitious sound (CAS) labels. HF_Tracheal_V1 and our previously built lung sound database, HF_Lung_V2, were either combined (mixed set), used one after the other (domain adaptation), or used alone to train convolutional neural network bidirectional gate recurrent unit models for inhalation, exhalation, and CAS detection in lung and tracheal sounds. The results revealed that the models trained using lung sound alone performed poorly in tracheal sound analysis and vice versa. However, mixed set training or domain adaptation improved the performance for 1) inhalation and exhalation detection in lung sounds and 2) inhalation, exhalation, and CAS detection in tracheal sounds compared to positive controls (the models trained using lung sound alone and used in lung sound analysis and vice versa). In particular, the model trained on the mixed set had great flexibility to serve two purposes, lung and tracheal sound analyses, at the same time.