Identificador persistente para citar o vincular este elemento: http://hdl.handle.net/10553/69730
Título: Voice Pathology Detection Using Deep Learning: A Preliminary Study
Autores/as: Harar, Pavol
Alonso-Hernández, Jesús B. 
Mekyska, Jiri
Galaz, Zoltan
Burget, Radim
Smekal, Zdenek
Clasificación UNESCO: 3307 Tecnología electrónica
Fecha de publicación: 2017
Editor/a: Institute of Electrical and Electronics Engineers (IEEE) 
Conferencia: 5th IEEE International Work Conference on Bio-Inspired Intelligence, IWOBI 2017 
Resumen: This paper describes a preliminary investigation of Voice Pathology Detection using Deep Neural Networks (DNN). We used voice recordings of sustained vowel /a/ produced at normal pitch from German corpus Saarbruecken Voice Database (SVD). This corpus contains voice recordings and electroglottograph signals of more than 2 000 speakers. The idea behind this experiment is the use of convolutional layers in combination with recurrent Long-Short-Term-Memory (LSTM) layers on raw audio signal. Each recording was split into 64 ms Hamming windowed segments with 30 ms overlap. Our trained model achieved 71.36% accuracy with 65.04% sensitivity and 77.67% specificity on 206 validation files and 68.08% accuracy with 66.75% sensitivity and 77.89% specificity on 874 testing files. This is a promising result in favor of this approach because it is comparable to similar previously published experiment that used different methodology. Further investigation is needed to achieve the state-of-the-art results.
URI: http://hdl.handle.net/10553/69730
ISBN: 9781538608500
DOI: 10.1109/IWOBI.2017.7985525
Fuente: 2017 International Work Conference on Bio-Inspired Intelligence: Intelligent Systems for Biodiversity Conservation, IWOBI 2017 - Proceedings, Funchal, e17032869
Colección:Actas de congresos
Vista completa

Citas SCOPUSTM   

77
actualizado el 24-mar-2024

Visitas

66
actualizado el 05-ago-2023

Google ScholarTM

Verifica

Altmetric


Comparte



Exporta metadatos



Los elementos en ULPGC accedaCRIS están protegidos por derechos de autor con todos los derechos reservados, a menos que se indique lo contrario.