TY  - JOUR
T1  - Gammachirp Wavelet and Neural Network for Identification of Pathological Voices
AU - , Lotfi Salhi AU - , Mourad Talbi AU - , Adnene Cherif 
JO  - Journal of Engineering and Applied Sciences
VL  - 3
IS  - 11
SP  - 822
EP  - 828
PY  - 2008
DA  - 2001/08/19
SN  - 1816-949x
DO  - jeasci.2008.822.828
UR  - https://makhillpublications.co/view-article.php?doi=jeasci.2008.822.828
KW  - Pathological voices
KW  -identification
KW  -cochlear filter
KW  -gammachirp model
KW  -wavelet transforms
KW  -neural networks
AB  - In this study, we present a new method for voice disorders identification based on a gammachirp wavelet transform and Multilayer Neural Network (MNN). The processing algorithm is based on a hybrid technique which uses the gammachirp wavelets coefficients as input of the MNN. The training step uses a speech database of several pathological and normal voices collected from the national hospital Rabta-Tunis and was conducted in a supervised mode for discrimination of normal and pathology voices and in a second step identification between neural and vocal pathologies (Parkinson, Alzheimer, laryngeal, dyslexia…). Several simulation results will be presented in function of the disease and will be compared with the clinical diagnosis in order to have an objective evaluation of the developed tool.
ER  -