Alongside the currently used nasal swab testing, the COVID-19 pandemic situation would gain notice-able advantages from low-cost tests that are available at any-time, anywhere, at a large-scale, and with real time answers. A novel approach for COVID-19 assessment is adopted here, discriminating negative subjects versus positive or recovered subjects. The scope is to identify potential discriminating features, highlight mid and short-term effects of COVID on the voice and compare two custom algorithms. A pool of 310 subjects took part in the study; recordings were collected in a low-noise, controlled setting employing three different vocal tasks. Binary classifications followed, using two different custom algorithms. The first was based on the coupling of boosting and bagging, with an AdaBoost classifier using Random Forest learners. A feature selection process was employed for the training, identifying a subset of features acting as clinically relevant biomarkers. The other approach was centered on two custom CNN architectures applied to mel-Spectrograms, with a custom knowledge-based data augmentation. Performances, evaluated on an independent test set, were comparable: Adaboost and CNN differentiated COVID-19 positive from negative with accuracies of 100% and 95% respectively, and recovered from negative individuals with accuracies of 86.1% and 75% respectively. This study highlights the possibility to identify COVID-19 positive subjects, foreseeing a tool for on-site screening, while also considering recovered subjects and the effects of COVID-19 on the voice. The two proposed novel architectures allow for the identification of biomarkers and demonstrate the ongoing relevance of traditional ML versus deep learning in speech analysis. (C) 2022 Elsevier B.V. All rights reserved.

Costantini, G., D, R., Robotti, C., Benazzo, M., Pietrantonio, F., Di Girolamo, S., et al. (2022). Deep learning and machine learning-based voice analysis for the detection of COVID-19: A proposal and comparison of architectures. KNOWLEDGE-BASED SYSTEMS, 253, 1-13 [10.1016/j.knosys.2022.109539].

Deep learning and machine learning-based voice analysis for the detection of COVID-19: A proposal and comparison of architectures

Costantini G.;Di Girolamo S.;Pisani A.;Saggio G.
2022-01-01

Abstract

Alongside the currently used nasal swab testing, the COVID-19 pandemic situation would gain notice-able advantages from low-cost tests that are available at any-time, anywhere, at a large-scale, and with real time answers. A novel approach for COVID-19 assessment is adopted here, discriminating negative subjects versus positive or recovered subjects. The scope is to identify potential discriminating features, highlight mid and short-term effects of COVID on the voice and compare two custom algorithms. A pool of 310 subjects took part in the study; recordings were collected in a low-noise, controlled setting employing three different vocal tasks. Binary classifications followed, using two different custom algorithms. The first was based on the coupling of boosting and bagging, with an AdaBoost classifier using Random Forest learners. A feature selection process was employed for the training, identifying a subset of features acting as clinically relevant biomarkers. The other approach was centered on two custom CNN architectures applied to mel-Spectrograms, with a custom knowledge-based data augmentation. Performances, evaluated on an independent test set, were comparable: Adaboost and CNN differentiated COVID-19 positive from negative with accuracies of 100% and 95% respectively, and recovered from negative individuals with accuracies of 86.1% and 75% respectively. This study highlights the possibility to identify COVID-19 positive subjects, foreseeing a tool for on-site screening, while also considering recovered subjects and the effects of COVID-19 on the voice. The two proposed novel architectures allow for the identification of biomarkers and demonstrate the ongoing relevance of traditional ML versus deep learning in speech analysis. (C) 2022 Elsevier B.V. All rights reserved.
2022
Pubblicato
Rilevanza internazionale
Articolo
Esperti anonimi
Settore ING-IND/31 - ELETTROTECNICA
English
1E, Vowel /e/ vocal task
2S, Sentence vocal task
3C, Cough vocal task
Adaboost
CFS, Correlation-based Feature Selection
CNN, Convolutional Neural Network
COVID-19
Classification
DL, Deep Learning
Deep learning
H, Healthy control subjects
MFCC, Mel-frequency Cepstral Coefficients
ML, Machine Learning
NS, Nasal Swab
P, Positive subjects
PCR, Polymerase Chain Reaction-based molecular swabs
PvsH, Positive versus Healthy subjects comparison
R, Recovered subjects
RF, Random Forest
ROC, Receiver-Operating Curve
ReLu, Rectified Linear Unit
RvsH, Recovered versus Healthy subjects comparison
SVM, Support Vector Machine
Speech processing
Costantini, G., D, R., Robotti, C., Benazzo, M., Pietrantonio, F., Di Girolamo, S., et al. (2022). Deep learning and machine learning-based voice analysis for the detection of COVID-19: A proposal and comparison of architectures. KNOWLEDGE-BASED SYSTEMS, 253, 1-13 [10.1016/j.knosys.2022.109539].
Costantini, G; D, Rvc; Robotti, C; Benazzo, M; Pietrantonio, F; Di Girolamo, S; Pisani, A; Canzi, P; Mauramati, S; Bertino, G; Cassaniti, I; Baldanti, F; Saggio, G
Articolo su rivista
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2108/331283
Citazioni
  • ???jsp.display-item.citation.pmc??? 5
  • Scopus 19
  • ???jsp.display-item.citation.isi??? 11
social impact