A new framework based on KNN and DT for speech identification through emphatic letters in Moroccan dialect

<p class="keywords"><span id="docs-internal-guid-6347807a-7fff-e7da-a2d6-74cb8393677f"><span>Arabic dialects differ substantially from modern standard arabic and each other in terms of phonology, morphology, lexical choice syntax. This makes the identification speeches a very difficult task. In this paper, we introduce speech recognition system that automatically identifies gender speaker, emphatic letter pronounced also diacritic these letters given sample author’s speeches. Firstly examined performance single case classifier hidden markov models (HMM) applied to samples our data corpus. Then evaluated proposed approach KNN-DT which is hybridization two classifiers namely decision trees (DT) k-nearest neighbors (KNN). Both are singularly directly corpus recognize sound speaker. proved quite interesting; it improved accuracy by more than 10% compared state-of-the-art approaches.</span></span></p>