Sorry, you need to enable JavaScript to visit this website.

FUSION OF MODULATION SPECTRAL AND SPECTRAL FEATURES WITH SYMPTOM METADATA FOR IMPROVED SPEECH-BASED COVID-19 DETECTION

Citation Author(s):
Tiago H. Falk
Submitted by:
Yi Zhu
Last updated:
4 May 2022 - 5:50pm
Document Type:
Presentation Slides
Document Year:
2022
Event:
Presenters:
Yi Zhu
Paper Code:
SS-15.1
Categories:
Keywords:
 

Existing speech-based coronavirus disease 2019 (COVID-19) detection systems provide poor interpretability and limited robustness to unseen data conditions. In this paper, we propose a system to overcome these limitations. In particular, we propose to fuse two different feature modalities with patient metadata in order to capture different properties of the disease. The first feature set is based on modulation spectral properties of speech. The second comprises spectral shape/descriptor features recently used for COVID-19 detection. Lastly, we fuse patient metadata in order to improve robustness and interpretability. Overall, a system relying on the fusion of all three modalities showed to be robust to unseen conditions and to rely on interpretable features.

up
0 users have voted: