Dysphonia is an often-underestimated vocal tract problem caused by irregular vocal cords vibration. It has been proved that dysphonia can be considered as a symptom of vocal tract diseases; also, voice anomalies represent neurological or neurodegenerative diseases triggers. Indeed, dysarthric voice patterns are studied as early detection for Parkinson's syndrome. Voice acoustic features can thus be extracted from simple vocalism (or short reading) and considered as diseases indicators. The interest is also improved thank to the possibility of using mobile and/or portable technologies to analyze voice parameters in a background manner. Nevertheless, voice can be considered as a personal signature, thus the identification of a general purpose features identification is still an open issue.In this work we focus on identifying voice signal features by using a comparative study of different classifiers. The target is to identify frequencies values and noise indexes (or combination of them) to be used as general purpose indicators, aiming to discriminate between healthy and pathological voices. The work is part of a larger project on voice analysis aiming to define a mobile and reliable based system allowing the acquisition and features extraction of vocal signals to be used as healthy monitor.

Voice Signal Features Analysis and Classification: Looking for New Diseases Related Parameters

Giuseppe Tradigo
;
Barbara Calabrese;Manuela Macri;Eugenio Vocaturo;Pierangelo Veltri
2015-01-01

Abstract

Dysphonia is an often-underestimated vocal tract problem caused by irregular vocal cords vibration. It has been proved that dysphonia can be considered as a symptom of vocal tract diseases; also, voice anomalies represent neurological or neurodegenerative diseases triggers. Indeed, dysarthric voice patterns are studied as early detection for Parkinson's syndrome. Voice acoustic features can thus be extracted from simple vocalism (or short reading) and considered as diseases indicators. The interest is also improved thank to the possibility of using mobile and/or portable technologies to analyze voice parameters in a background manner. Nevertheless, voice can be considered as a personal signature, thus the identification of a general purpose features identification is still an open issue.In this work we focus on identifying voice signal features by using a comparative study of different classifiers. The target is to identify frequencies values and noise indexes (or combination of them) to be used as general purpose indicators, aiming to discriminate between healthy and pathological voices. The work is part of a larger project on voice analysis aiming to define a mobile and reliable based system allowing the acquisition and features extraction of vocal signals to be used as healthy monitor.
2015
9781450338530
classification, voice monitoring, acoustic features extraction, machine learning, dysphonia
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/342379
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact