Cepstral Analysis of Speech for the Vocal Fold Pathology Detection

Saldanha, Jennifer C and Ananthakrishna, T and Pinto, Rohan (2012) Cepstral Analysis of Speech for the Vocal Fold Pathology Detection. In: Proceedings of ICEDSP ’12, MIT, Manipal, 20-22 December 2012, MIT, Manipal..

[img] PDF
505.pdf - Published Version
Restricted to Registered users only

Download (129kB) | Request a copy


It is possible to identify voice disorders using certain features of speech signals. A complementary technique could be acoustic analysis of the speech signal, which is shown to be a potentially useful tool to detect voice diseases[2]. The focus of this study is to compare the performances of mel-frequency cepstral coefficients MFCC) and linear predictive cepstral coefficients (LPCC) features in the detection of vocal fold pathology and also bring out scale to measure severity of the disease. The speech processing algorithm proposed estimates features necessary to formulate a stochastic model to characterize healthy and pathology conditions from speech recordings. Two different set of features such as MFCC and LPCC are extracted from acoustic analysis of voiced speech of normal and pathological subjects. A linear discriminant analysis (LDA) classifier is designed and the classification results have been reported.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Mel frequency cepstral coefficients, Linear predictive cepstral coefficients, Linear discriminant analysis.
Subjects: Engineering > MIT Manipal > Electronics and Communication
Depositing User: Anantha krishna T
Date Deposited: 21 Oct 2013 09:26
Last Modified: 25 Feb 2015 05:02
URI: http://eprints.manipal.edu/id/eprint/137539

Actions (login required)

View Item View Item