Acoustic Analysis of Phonetics of Arabic Script Sindhi Language to evaluate Vowel-Consonant Segmentation

Abstract

This paper proposes an efficient speech recognition method for any spoken language of the world in general and Arabic script languages, including Arabic, Urdu, and Sindhi etc, in particular. For the purpose, Sindhi has been selected as an example language, since it has a superset of all other Arabic script languages’ phonemes and research has been conducted in two major areas including the definition and refinement of standard phonemes for Sindhi language comprising of vowels, semi-vowels, diphthongs, and consonants as defined by International Phonetic Association (IPA) and acoustic analysis of phonetics for Sindhi which includes analysis of waveforms, Linear Predictive Coefficient (LPC), and spectrographic characterizations, especially formants, of some of the phonemes, to identify the categorical properties of these phonemes and their boundary detection in an utterance. The objective is to provide a guideline and solid foundation for development of efficient speech recognition systems for Sindhi language in particular and all Arabic script languages in general.