Classification of Adventitious Sounds Combining Cochleogram and Vision Transformers

TL;DR

This study explores using cochleogram inputs with Vision Transformers for classifying respiratory adventitious sounds, demonstrating superior performance over traditional CNN methods on the ICBHI dataset.

Contribution

First application of cochleogram with Vision Transformer architecture for adventitious sound classification, showing improved accuracy over existing CNN approaches.

Findings

Cochleogram combined with ViT outperforms CNN methods.

ViT demonstrates promising results in respiratory sound classification.

The approach enhances automatic detection of respiratory irregularities.

Abstract

Early identification of respiratory irregularities is critical for improving lung health and reducing global mortality rates. The analysis of respiratory sounds plays a significant role in characterizing the respiratory system's condition and identifying abnormalities. The main contribution of this study is to investigate the performance when the input data, represented by cochleogram, is used to feed the Vision Transformer architecture, since this input classifier combination is the first time it has been applied to adventitious sound classification to our knowledge. Although ViT has shown promising results in audio classification tasks by applying self attention to spectrogram patches, we extend this approach by applying the cochleogram, which captures specific spectro-temporal features of adventitious sounds. The proposed methodology is evaluated on the ICBHI dataset. We compare the classification performance of ViT with other state of the art CNN approaches using spectrogram, Mel frequency cepstral coefficients, constant Q transform, and cochleogram as input data. Our results confirm the superior classification performance combining cochleogram and ViT, highlighting the potential of ViT for reliable respiratory sound classification. This study contributes to the ongoing efforts in developing automatic intelligent techniques with the aim to significantly augment the speed and effectiveness of respiratory disease detection, thereby addressing a critical need in the medical field.