Improved Techniques for the Conditional Generative Augmentation of Clinical Audio Data

by   Mane Margaryan, et al.

Data augmentation is a valuable tool for the design of deep learning systems to overcome data limitations and stabilize the training process. Especially in the medical domain, where the collection of large-scale data sets is challenging and expensive due to limited access to patient data, relevant environments, as well as strict regulations, community-curated large-scale public datasets, pretrained models, and advanced data augmentation methods are the main factors for developing reliable systems to improve patient care. However, for the development of medical acoustic sensing systems, an emerging field of research, the community lacks large-scale publicly available data sets and pretrained models. To address the problem of limited data, we propose a conditional generative adversarial neural network-based augmentation method which is able to synthesize mel spectrograms from a learned data distribution of a source data set. In contrast to previously proposed fully convolutional models, the proposed model implements residual Squeeze and Excitation modules in the generator architecture. We show that our method outperforms all classical audio augmentation techniques and previously published generative methods in terms of generated sample quality and a performance improvement of 2.84 enhancement of 1.14% in relation to previous work. By analyzing the correlation of intermediate feature spaces, we show that the residual Squeeze and Excitation modules help the model to reduce redundancy in the latent features. Therefore, the proposed model advances the state-of-the-art in the augmentation of clinical audio data and improves the data bottleneck for the design of clinical acoustic sensing systems.


page 6

page 7


Conditional Generative Data Augmentation for Clinical Audio Datasets

In this work, we propose a novel data augmentation method for clinical a...

Environment Transfer for Distributed Systems

Collecting sufficient amount of data that can represent various acoustic...

Data augmentation using generative networks to identify dementia

Data limitation is one of the most common issues in training machine lea...

Improving prostate whole gland segmentation in t2-weighted MRI with synthetically generated data

Whole gland (WG) segmentation of the prostate plays a crucial role in de...

Evaluation of Deep Convolutional Generative Adversarial Networks for data augmentation of chest X-ray images

Medical image datasets are usually imbalanced, due to the high costs of ...

A Pressure Ulcer Care System For Remote Medical Assistance: Residual U-Net with an Attention Model Based for Wound Area Segmentation

Increasing numbers of patients with disabilities or elderly people with ...

Data generator based on RBF network

There are plenty of problems where the data available is scarce and expe...

Please sign up or login with your details

Forgot password? Click here to reset