Title
Feature Estimation for Vocal Fold Edema Detection Using Short-Term Cepstral Analysis.
Abstract
Digital signal processing techniques have been used to perform an acoustic analysis for vocal quality assessment due to the simplicity and the noninvasive nature of the measurement procedures. Their employment is of special interest, as they can provide an objective diagnosis of pathological voices, and may be used as complementary tool in laryngoscope exams. The acoustic modeling of pathological voices is very important to discriminate normal and pathological voices. The degree of reliability and effectiveness of the discriminating process depends on the appropriate acoustic feature extraction. This paper aims at specifying and evaluating the acoustic features for vocal fold edema through a parametric modeling approach based on the resonant structure of the human speech production mechanism, and a nonparametric approach related to human auditory perception system. For this purpose, LPC and LPC-based cepstral coefficients, and mel-frequency cepstral coefficients are used. A vector-quantizing-trained distance classifier is used in the discrimination process.
Year
DOI
Venue
2007
10.1109/BIBE.2007.4375707
BIBE
Keywords
Field
DocType
speech processing,lpc,bioacoustics,feature extraction,digital signal processing,speech production,speech pathology,mel frequency cepstral coefficient,speech,parametric model,mel frequency cepstral coefficients
Mel-frequency cepstrum,Speech processing,Digital signal processing,Pattern recognition,Computer science,Bioacoustics,Nonparametric statistics,Speech recognition,Feature extraction,Artificial intelligence,Classifier (linguistics),Speech production
Conference
ISBN
Citations 
PageRank 
978-1-4244-1509-0
3
0.43
References 
Authors
7
4
Name
Order
Citations
PageRank
Benedito G. Aguiar Neto1255.06
J M Fechine2204.13
Silvana Cunha Costa3123.51
Menaka Muppa430.77