TY - GEN
T1 - Transformer-based CNNs
T2 - 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021
AU - Chang, Yi
AU - Ren, Zhao
AU - Schuller, Bjorn W.
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Due to the COronaVIrus Disease 2019 (COVID-19) pandemic, early screening of COVID-19 is essential to prevent its transmission. Detecting COVID-19 with computer audition techniques has in recent studies shown the potential to achieve a fast, cheap, and ecologically friendly diagnosis. Respiratory sounds and speech may contain rich and complementary information about COVID-19 clinical conditions. Therefore, we propose training three deep neural networks on three types of sounds (breathing/counting/vowel) and assembling these models to improve the performance. More specifically, we employ Convolutional Neural Networks (CNNs) to extract spatial representations from log Mel spectrograms and a multi-head attention mechanism in the transformer to mine temporal context information from the CNNs' outputs. The experimental results demonstrate that the transformer-based CNNs can effectively detect COVID-19 on the DiCOVA Track-2 database (AUC: 70.0%) and outperform simple CNNs and hybrid CNN-RNNs.
AB - Due to the COronaVIrus Disease 2019 (COVID-19) pandemic, early screening of COVID-19 is essential to prevent its transmission. Detecting COVID-19 with computer audition techniques has in recent studies shown the potential to achieve a fast, cheap, and ecologically friendly diagnosis. Respiratory sounds and speech may contain rich and complementary information about COVID-19 clinical conditions. Therefore, we propose training three deep neural networks on three types of sounds (breathing/counting/vowel) and assembling these models to improve the performance. More specifically, we employ Convolutional Neural Networks (CNNs) to extract spatial representations from log Mel spectrograms and a multi-head attention mechanism in the transformer to mine temporal context information from the CNNs' outputs. The experimental results demonstrate that the transformer-based CNNs can effectively detect COVID-19 on the DiCOVA Track-2 database (AUC: 70.0%) and outperform simple CNNs and hybrid CNN-RNNs.
UR - https://www.scopus.com/pages/publications/85122503796
U2 - 10.1109/EMBC46164.2021.9629552
DO - 10.1109/EMBC46164.2021.9629552
M3 - Conference contribution
C2 - 34891751
AN - SCOPUS:85122503796
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 2335
EP - 2338
BT - 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 1 November 2021 through 5 November 2021
ER -