DocumentCode
2317167
Title
Pathological Assesment of Vocal Fold Nodules and Polyp Using Accoustic Perturbation and Phase Space Features
Author
Behroozmand, Roozbeh ; Almasganj, Farshad ; Moradi, Mohammad Hassan
Author_Institution
Fac. of Biomed. Eng., Amirkabir Univ. of Technol., Tehran
Volume
2
fYear
2006
fDate
14-19 May 2006
Abstract
In this study, investigations are carried out from the speech waveform of the patients whose vocal folds vibration pattern has been affected by the presence of nodules and polyp. Acoustic, pitch and amplitude perturbation quotients, and nonlinear dynamic measures, phase space reconstruction and correlation dimension, are scrutinized to analyze a sustained vowel pronounced by these individuals. It is found that the cycle-to-cycle pitch frequency and amplitude variation in the case of polyp is higher than nodules. It is also demonstrated that patients´ voice signals with nodules, in comparison with polyp, has lower-dimensional phase space dynamical characteristics. Classification procedure implemented using support vector machine shows that nonlinear dynamical features provide us with a more prominent description of such benign vocal fold pathologies as a valuable tool for clinical diagnosis applications
Keywords
acoustics; medical signal processing; patient diagnosis; signal classification; signal reconstruction; speech processing; support vector machines; acoustic perturbation; amplitude perturbation quotients; benign vocal fold pathologies; classification procedure; clinical diagnosis applications; correlation dimension; cycle-to-cycle pitch frequency; nonlinear dynamic measures; nonlinear dynamical features; pathological assessment; phase space features; phase space reconstruction; pitch perturbation quotients; polyp; speech waveform; support vector machine; vocal fold nodules; vocal folds vibration pattern; Acoustic measurements; Clinical diagnosis; Extraterrestrial measurements; Frequency; Nonlinear acoustics; Pathology; Phase measurement; Speech; Support vector machine classification; Support vector machines;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location
Toulouse
ISSN
1520-6149
Print_ISBN
1-4244-0469-X
Type
conf
DOI
10.1109/ICASSP.2006.1660528
Filename
1660528
Link To Document