Sound Signal Synthesis with Auxiliary Classifier GAN, COVID-19 cough as an example

2025-08-12

AI Summary

Limited availability of COVID-19 cough audio data constrains the performance of automatic classification models. Method: We propose a Mel-spectrogram conditional generation approach based on Auxiliary Classifier Generative Adversarial Networks (ACGAN), where disease labels (healthy vs. COVID-19–positive) serve as conditioning inputs to synthesize high-fidelity, class-discriminative spectrograms. This augments small-scale training sets effectively. Contribution/Results: Evaluated using a CNN classifier on a subset of the Coughvid dataset, our method improves test accuracy from 72% to 75%, demonstrating that synthetically generated data significantly enhances generalization in low-resource medical audio classification. To the best of our knowledge, this is the first work to systematically apply conditional GANs to COVID-19 cough spectrogram generation. The proposed framework provides a practical, lightweight data augmentation paradigm for rapid deployment of auscultation-based diagnostic models in emergency public health scenarios.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

One of the fastest-growing domains in AI is healthcare. Given its importance, it has been the interest of many researchers to deploy ML models into the ever-demanding healthcare domain to aid doctors and increase accessibility. Delivering reliable models, however, demands a sizable amount of data, and the recent COVID-19 pandemic served as a reminder of the rampant and scary nature of healthcare that makes training models difficult. To alleviate such scarcity, many published works attempted to synthesize radiological cough data to train better COVID-19 detection models on the respective radiological data. To accommodate the time sensitivity expected during a pandemic, this work focuses on detecting COVID-19 through coughs using synthetic data to improve the accuracy of the classifier. The work begins by training a CNN on a balanced subset of the Coughvid dataset, establishing a baseline classification test accuracy of 72%. The paper demonstrates how an Auxiliary Classification GAN (ACGAN) may be trained to conditionally generate novel synthetic Mel Spectrograms of both healthy and COVID-19 coughs. These coughs are used to augment the training dataset of the CNN classifier, allowing it to reach a new test accuracy of 75%. The work highlights the expected messiness and inconsistency in training and offers insights into detecting and handling such shortcomings.

Problem

• Synthesizing COVID-19 cough data for training AI models
• Improving COVID-19 detection accuracy using synthetic cough sounds
• Addressing data scarcity in healthcare with ACGAN-generated samples

Innovation

• Uses ACGAN for synthetic cough data generation
• Augments CNN training with synthetic Mel Spectrograms
• Improves COVID-19 cough classification accuracy