Distinguish the Severity of Illness Associated with Novel Coronavirus (COVID-19) Infection via Sustained Vowel Speech Features.
Int J Environ Res Public Health
; 20(4)2023 02 15.
Article
en En
| MEDLINE
| ID: mdl-36834110
ABSTRACT
The authors are currently conducting research on methods to estimate psychiatric and neurological disorders from a voice by focusing on the features of speech. It is empirically known that numerous psychosomatic symptoms appear in voice biomarkers; in this study, we examined the effectiveness of distinguishing changes in the symptoms associated with novel coronavirus infection using speech features. Multiple speech features were extracted from the voice recordings, and, as a countermeasure against overfitting, we selected features using statistical analysis and feature selection methods utilizing pseudo data and built and verified machine learning algorithm models using LightGBM. Applying 5-fold cross-validation, and using three types of sustained vowel sounds of /Ah/, /Eh/, and /Uh/, we achieved a high performance (accuracy and AUC) of over 88% in distinguishing "asymptomatic or mild illness (symptoms)" and "moderate illness 1 (symptoms)". Accordingly, the results suggest that the proposed index using voice (speech features) can likely be used in distinguishing the symptoms associated with novel coronavirus infection.
Palabras clave
Texto completo:
1
Bases de datos:
MEDLINE
Asunto principal:
Coronavirus
/
COVID-19
Tipo de estudio:
Risk_factors_studies
Límite:
Humans
Idioma:
En
Revista:
Int J Environ Res Public Health
Año:
2023
Tipo del documento:
Article
País de afiliación:
Japón