Open AccessEnergy distribution in formant bands for arabic vowels
Author(s) -
Mohamed Farchi,
Karim Tahiry,
mounir Soufyane,
Badia Mounir,
Ahmed Mouhsen
Publication year - 2019
Publication title -
international journal of electrical and computer engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.277
H-Index - 22
ISSN - 2088-8708
DOI - 10.11591/ijece.v9i2.pp1163-1167
Subject(s) - formant , voice , speech recognition , computer science , energy (signal processing) , arabic , segmentation , acoustics , signal (programming language) , degree (music) , work (physics) , vowel , mathematics , artificial intelligence , linguistics , physics , statistics , philosophy , programming language , thermodynamics
The acoustic cues play a major role in speech segmentation phase; the extraction of these indexes facilitates the characterization of the speech signal. In this work, we aim to study Arabic vowels (/a/, /a:/, /i/, /i:/, /u/ and /u:/), especially the long ones. We are interested in characterizing this type of vowels in terms of time, frequency and energy. The cues extracted and analyzed in this work are: segment length, voicing degree and formants values.