Using Human Factor Cepstral Coefficient on Multiple Types of Voice Recordings for Detecting Patients with Parkinson's Disease - 14/11/17
pages | 6 |
Iconographies | 2 |
Vidéos | 0 |
Autres | 0 |
Abstract |
In this study, we wanted to discriminate between two groups of participants (patients with Parkinson's disease and healthy people) by analyzing 3 types of voice recordings. Firstly we collected multiple types of voice recording of three sustained vowels /a/, /o/ and /u/ at a comfortable level which was collected from the 40 participants (20 PD and 20 healthy). The technique used in this study is to extract Human Factor Cepstral Coefficients (HFCC). The extracted HFCC were compressed by calculating their average value in order to get the Voiceprint from each voice recording. Subsequently, a classification method was performed using Leave One Subject Out validation scheme along with supervised learning classifiers. We used SVM with its four different kernels (RBF, Linea, Polynomial and MLP), and k-nearest neighbored ( , 5 and 7). Based on the research result, the best obtained classification accuracy was 87.5% using linear kernel of SVM with the first 14 cepstral coefficients of the HFCC and 100% using the test database.
Le texte complet de cet article est disponible en PDF.Graphical abstract |
Highlights |
• | Collection of multiple types of voice recordings. |
• | Extraction of the HFCC from all voice samples. |
• | Extraction of the voiceprint from each voice sample. |
• | Classification using SVM, KNN along with LOSO validation scheme. |
• | We obtained 100% as a maximum classification accuracy. |
Keywords : Voice analysis, Parkinson's disease, Acoustic features, Human factor cepstral coefficient, Leave one subject out, Support vector machines
Plan
Vol 38 - N° 6
P. 346-351 - novembre 2017 Retour au numéroBienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’achat d’article à l’unité est indisponible à l’heure actuelle.
Déjà abonné à cette revue ?