| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 4.53 MB | Adobe PDF |
Advisor(s)
Abstract(s)
Este trabalho propõe métodos de discriminação automática entre pacientes diagnosticados com Esclerose Lateral Amiotrófica (ELA) bulbar e oradores saudáveis, a partir da extração de parâmetros do espetro de sinais de voz. Os testes com validação cruzada obtiveram uma taxa de acertos máxima num conjunto de teste de 80% e 82.4%, com os classificadores Linear Discriminant Analysis e Support Vector Classifier, respetivamente. Os resultados obtidos estão em linha com os propostos no estudo prévio quando considerado o declive espetral nas altas frequências.
This work presents methods of discrimination between patients diagnosed with bulbar Amyotrophic Lateral Sclerosis (ALS) and healthy speakers, based on the extraction of parameters from the voice signal spectrum. Testes using k-cross-validation achieved a maximum accuracy in the test fold of 80% and 82.4% with a Linear Discriminant Analysis classifier and a Support Vector Classifier, respectively. The results obtained are in line with those proposed in the previous study when considering the spectral slope at high frequencies.
This work presents methods of discrimination between patients diagnosed with bulbar Amyotrophic Lateral Sclerosis (ALS) and healthy speakers, based on the extraction of parameters from the voice signal spectrum. Testes using k-cross-validation achieved a maximum accuracy in the test fold of 80% and 82.4% with a Linear Discriminant Analysis classifier and a Support Vector Classifier, respectively. The results obtained are in line with those proposed in the previous study when considering the spectral slope at high frequencies.
Description
Keywords
Análise espetral Vozes patológicas Esclerose lateral amiotrófica Classificação Avaliação Spectral analysis Pathological voices Amyothrophic lateral sclerosis Classification Evaulation
Citation
COTTER, Sofia; CORDEIRO, Hugo; MARQUES, Gonçalo – Classification of patients diagnosed with ALS through spectral parameters : comparison between automatic classifiers and visual methos. In 17th Iberian Conference on Information Systems and Technologies (CISTI). Madrid, Spain: IEEE, 2022. ISBN 978-9-8933-3436-2. Pp. 1-6.
Publisher
IEEE