Statistical modeling for dysphonic classification

Author

Ghelis, Assia ; Guerti, Mhania ; Fredouille, Corinne

Author_Institution

LEREC Lab., Badji Mokhtar Univ., Annaba, Algeria

fYear

2010

fDate

23-25 March 2010

Firstpage

1

Lastpage

4

Abstract

The objective of our work is to develop an automatic system to evaluate Arabic/French dysphonic classification by modeling speech signals using a statistical modeling based on a Gaussian Mixture Model (GMM), which is state of art in speaker recognition. Speakers were conducted at Annaba University Hospital center (CHU) in the ENT service in the presence of a group composed of 8 medical specialists. Results of the experiment show that an automatic system is able to identify dysphonic speakers with an acceptable performance either in French or in Arabic language.

Keywords

Gaussian processes; natural language processing; pattern classification; speaker recognition; statistical analysis; Annaba University Hospital center; Arabic language; Gaussian mixture model; automatic system; dysphonic classification; speaker recognition; speech signals; statistical modeling; Acoustic measurements; Acoustic signal detection; Frequency; Hospitals; Laboratories; Loudspeakers; Natural languages; Pathology; Speaker recognition; Speech analysis; GMM; Speaker recognition; dysphonia;

fLanguage

English

Publisher

ieee

Conference_Titel

Design and Technology of Integrated Systems in Nanoscale Era (DTIS), 2010 5th International Conference on

Conference_Location

Hammamet

Print_ISBN

978-1-4244-6338-1

Type

conf

DOI

10.1109/DTIS.2010.5487588

Filename

5487588