Abstract
This work aims to detect vocal disorders related to vocal nodule, Reinke’s edema and neurological pathologies through multiband cepstral measures of the sustained vowel/a/. Detection is performed between pairs of study groups and multiband analysis is accomplished using the Wavelet transform. For each pair of groups, a parameters selection is performed. Statistics of the selected parameters are used as input for four classifiers with leave-one-out cross validation. Classification accuracies equal or greater than 96.70% are obtained for 6pairs of study groups while only 74.20% is achieved for the Edema/Nodule pair
Original language | Portuguese |
---|---|
Number of pages | 5 |
DOIs | |
Publication status | Published - Nov 2020 |
Event | XXXVIII Simpósio Brasileiro de Telecomunicações e Processamento de Sinais - Florianópolis, Brazil Duration: 22 Nov 2020 → 25 Nov 2020 https://biblioteca.sbrt.org.br/events/13 |
Conference
Conference | XXXVIII Simpósio Brasileiro de Telecomunicações e Processamento de Sinais |
---|---|
Country/Territory | Brazil |
City | Florianópolis |
Period | 22/11/20 → 25/11/20 |
Internet address |
Keywords
- Voice disorders detection
- Vocal fold
- Reinke’s edema
- Neurological pathologies
- Cepstral measures
- Wavelet