Please use this identifier to cite or link to this item:
Title: Yet another approach for the measurement of the degree of voice normality: A simple scheme based on feature reduction and single Gaussian distributions
Authors: Ykhlef, Fay
Benzaba, W.
Boutaleb, R.
Alonso-Hernández, Jesús B. 
Ykhlef, Far
UNESCO Clasification: 240601 Bioacústica
120325 Diseño de sistemas sensores
Keywords: Cepstral parameters
Degree of voice normality
Fisher's linear discriminant
Single distributions
Issue Date: 2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Conference: IEEE International Symposium on Multimedia (ISM) 
Abstract: In this paper, we propose another approach for the measurement of the degree of voice normality based on statistical modeling. The basic methodology behind the proposed approach is the «Pathological Likelihood Index» reported by Godino-Llorente JI. et al. [1]. The major innovations are: exploring a reduced set of Mel frequency cepstral coefficients (MFCC) and ignoring their derivatives, a linear projection of MFCCs into one dimensional space using Fisher's linear discriminant, and, modeling build around single Gaussian distributions instead of mixtures of distributions. We have evaluated the proposed approach using the Massachusetts Eye and Ear Infirmary database (MEEI). The obtained results are better than the one reported in [1].
ISBN: 978-1-5090-0379-2
DOI: 10.1109/ISM.2015.23
Source: Proceedings - 2015 IEEE International Symposium on Multimedia, ISM 2015, p. 335-338, (Marzo 2016)
Appears in Collections:Actas de congresos
Show full item record

Page view(s)

checked on Feb 21, 2021

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.