1.0 KiB
1.0 KiB
layout, title, categories, excerpt, header
| layout | title | categories | excerpt | header | ||
|---|---|---|---|---|---|---|
| single | Surgical Mask Detection | research audio deep-learning | Convolutional Neural Networks and Data Augmentations on Spectrograms |
|
{:style="display:block; width:80%" .align-center}
This study assesses the effectiveness of data augmentation in enhancing neural network models for audio data classification, focusing on mel-spectrogram representations. Specifically, it examines the role of data augmentation in improving the performance of convolutional neural networks for detecting the presence of surgical masks from human voice samples, testing across four different network architectures. The findings indicate a significant enhancement in model performance, surpassing many of the existing benchmarks established by the ComParE challenge. For further details, refer to {% cite illium2020surgical %}.
{:style="display:block; width:80%" .align-center}