TY - GEN

T1 - Convoluational Transformer With Adaptive Position Embedding For Covid-19 Detection From Cough Sounds

AU - Yan, Tianhao

AU - Meng, Hao

AU - Liu, Shuo

AU - Parada-Cabaleiro, Emilia

AU - Ren, Zhao

AU - Schuller, Björn W.

PY - 2022

Y1 - 2022

N2 - Covid-19 has caused a huge health crisis worldwide in the past two years. Although an early detection of the virus through nucleic acid screening can considerably reduce its spread, the efficiency of this diagnostic process is limited by its complexity and costs. Hence, an effective and inexpensive way to early detect Covid-19 is still needed. Considering that the cough of an infected person contains a large amount of information, we propose an algorithm for the automatic recognition of Covid-19 from cough signals. Our approach generates static log-Mel spectrograms with deltas and delta-deltas from the cough signal and subsequently extracts feature maps through a Convolutional Neural Network (CNN). Following the advances on transformers in the realm of deep learning, our proposed architecture exploits a novel adaptive position embedding structure which can learn the position information of the features from the CNN output. This make the transformer structure rapidly lock the attention feature location by overlaying with the CNN output, which yields better classification. The efficiency of the proposed architecture is shown by the improvement, w. r. t. the baseline, of our experimental results on the INTERPSEECH 2021 Computational Paralinguistics Challenge CCS (Coughing Sub Challenge) database, which reached 72.6 % UAR (Unweighted Average Recall).

AB - Covid-19 has caused a huge health crisis worldwide in the past two years. Although an early detection of the virus through nucleic acid screening can considerably reduce its spread, the efficiency of this diagnostic process is limited by its complexity and costs. Hence, an effective and inexpensive way to early detect Covid-19 is still needed. Considering that the cough of an infected person contains a large amount of information, we propose an algorithm for the automatic recognition of Covid-19 from cough signals. Our approach generates static log-Mel spectrograms with deltas and delta-deltas from the cough signal and subsequently extracts feature maps through a Convolutional Neural Network (CNN). Following the advances on transformers in the realm of deep learning, our proposed architecture exploits a novel adaptive position embedding structure which can learn the position information of the features from the CNN output. This make the transformer structure rapidly lock the attention feature location by overlaying with the CNN output, which yields better classification. The efficiency of the proposed architecture is shown by the improvement, w. r. t. the baseline, of our experimental results on the INTERPSEECH 2021 Computational Paralinguistics Challenge CCS (Coughing Sub Challenge) database, which reached 72.6 % UAR (Unweighted Average Recall).

KW - Adaptive Position Embedding Transformer

KW - Computer Audition

KW - Convolutional Neural Network

KW - log-Mel Spectrogram

KW - SARS-CoV2 Detection

UR - http://www.scopus.com/inward/record.url?scp=85131243911&partnerID=8YFLogxK

U2 - 10.1109/icassp43922.2022.9747513

DO - 10.1109/icassp43922.2022.9747513

M3 - Conference contribution

AN - SCOPUS:85131243911

SN - 978-1-6654-0541-6

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 9092

EP - 9096

BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022

Y2 - 23 May 2022 through 27 May 2022

ER -