<span>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.</span>
Vowels are the primary units of a sound system of a language. The classification of these vowels is therefore very important for the recognition and synthesis of speech. In this paper, we propose a normalized energy-based approach in formants and pitch to characterize Arabic vowels (short vowels: / a /, / i /, / u /; long vowels: / a: /, / i: /, / u: /). The classification was performed using a developed algorithm on records extracted from an Arabic corpus after the extraction of the pitch and the first three formants and the computation of the normalized energy in these bands. The results showed that the algorithm distinguishes Arabic vowels by analyzing the normalized energy in the nucleus of F1, F2, and F3 formants and pitch F0 with a rate of 88.7% for long vowels and a rate of 90% for short vowels.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.