A Deep Learning Architecture with Spatio-Temporal Focusing for Detecting Respiratory Anomalies
Abstract
This paper presents a deep learning system applied for detecting anomalies from respiratory sound recordings. Our system initially performs audio feature extraction using Continuous Wavelet transformation. This transformation converts the respiratory sound input into a two-dimensional spectrogram where both spectral and temporal features are presented. Then, our proposed deep learning architecture inspired by the Inception-residual-based backbone performs the spatial-temporal focusing and multi-head attention mechanism to classify respiratory anomalies. In this work, we evaluate our proposed models on the benchmark SPRSound (The Open-Source SJTU Paediatric Respiratory Sound) database proposed by the IEEE BioCAS 2023 challenge. As regards the Score computed by an average between the average score and harmonic score, our robust system has achieved Top-1 performance with Scores of 0.810, 0.667, 0.744, and 0.608 in Tasks 1-1, 1-2, 2-1, and 2-2, respectively.
Keywords
Cite
@article{arxiv.2306.14929,
title = {A Deep Learning Architecture with Spatio-Temporal Focusing for Detecting Respiratory Anomalies},
author = {Dat Ngo and Lam Pham and Huy Phan and Minh Tran and Delaram Jarchi},
journal= {arXiv preprint arXiv:2306.14929},
year = {2023}
}
Comments
arXiv admin note: text overlap with arXiv:2303.04104