Arabic vowels characterization and classification using the normalized energy in frequency bands

Abstract

The main objective of this work is to conduct an acoustic study of Arabic vowels (/a/, /a:/, /u/, /u:/, /i/ and /i:/) in order to determine the most relevant characteristics that allow recognizing these vowels. The analysis of vowel spectrograms reveals that the energy distribution as a function of time and frequency clearly differs according to the considered vowel. Thus, we used the normalized energy in frequency bands to classify these vowels. Thereafter, we have exploited the obtained results to develop algorithms that allow the classification of vowels and the distinction of the long vowels from the short ones. The efficiency of these algorithms was evaluated by testing their performances on our Arabic corpus.

Arabic vowels characterization and classification using the normalized energy relating to formants and pitch

“…It was possible to differentiate between short and long vowels. These results are very competitive compared to those reported in the literature [23], [25]- [27].…”

“…Another aspect of the study was able to demonstrate that the energy distribution in the frequency bands can characterize Arabic vowels according to the duration of production. Furthermore, the percentage distribution of energy in these frequency bands appears to be unaffected by the time of production [23]. Due to the distribution of formants F1 and F2, they demonstrated that the majority of energy for the vowel /a/ is located in the first five bands B1, B2, B3, B4, and B5.…”