# Robust Deep Learning Framework For Predicting Respiratory Anomalies and Diseases

arXiv: https://arxiv.org/abs/2002.03894 · HTML: https://mlsanity.com/paper/2002.03894/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2020.

## Built on by (most cited first, 11 of 11)

- [Lung Sound Classification Using Co-tuning and Stochastic Normalization](https://mlsanity.com/paper/2108.01991/) (2021)
- [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)
- [COVID-19 Detection from Respiratory Sounds with Hierarchical Spectrogram Transformers](https://mlsanity.com/paper/2207.09529/) (2022)
- [Crackle Detection In Lung Sounds Using Transfer Learning And Multi-Input Convolitional Neural Networks](https://mlsanity.com/paper/2104.14921/) (2021)
- [Multimedia Datasets for Anomaly Detection: A Review](https://mlsanity.com/paper/2112.05410/) (2021)
- [Multi-path Convolutional Neural Networks Efficiently Improve Feature Extraction in Continuous Adventitious Lung Sound Detection](https://mlsanity.com/paper/2107.04226/) (2021)
- [Variational Autoencoders for Anomaly Detection in Respiratory Sounds](https://mlsanity.com/paper/2208.03326/) (2022)
- [Rene: A Pre-trained Multi-modal Architecture for Auscultation of Respiratory Diseases](https://mlsanity.com/paper/2405.07442/) (2024)
- [Chronic Obstructive Pulmonary Disease Prediction Using Deep Convolutional Network](https://mlsanity.com/paper/2411.02449/) (2024)
- [A Multi-Stage Hybrid CNN-Transformer Network for Automated Pediatric Lung Sound Classification](https://mlsanity.com/paper/2507.20408/) (2025)
- [Explainable Multi-Modal Deep Learning for Automatic Detection of Lung Diseases from Respiratory Audio Signals](https://mlsanity.com/paper/2512.00563/) (2025)

## Abstract (arXiv)

This paper presents a robust deep learning framework developed to detect respiratory diseases from recordings of respiratory sounds. The complete detection process firstly involves front end feature extraction where recordings are transformed into spectrograms that convey both spectral and temporal information. Then a back-end deep learning model classifies the features into classes of respiratory disease or anomaly. Experiments, conducted over the ICBHI benchmark dataset of respiratory sounds, evaluate the ability of the framework to classify sounds. Two main contributions are made in this paper. Firstly, we provide an extensive analysis of how factors such as respiratory cycle length, time resolution, and network architecture, affect final prediction accuracy. Secondly, a novel deep learning based framework is proposed for detection of respiratory diseases and shown to perform extremely well compared to state of the art methods.