@inproceedings{b262a72ad8c44c96a695e993b57a1684,
title = "QMDIS: QCRI-MIT advanced dialect identification system",
abstract = "As a continuation of our efforts towards tackling the problem of spoken Dialect Identification (DID) for Arabic languages, we present the QCRI-MIT Advanced Dialect Identification System (QMDIS). QMDIS is an automatic spoken DID system for Dialectal Arabic (DA). In this paper, we report a comprehensive study of the three main components used in the spoken DID task: phonotactic, lexical and acoustic. We use Support Vector Machines (SVMs), Logistic Regression (LR) and Convolutional Neural Networks (CNNs) as backend classifiers throughout the study. We perform all our experiments on a publicly available dataset and present new state-of-The-Art results. QMDIS discriminates between the five most widely used dialects of Arabic: namely Egyptian, Gulf, Levantine, North African, and Modern Standard Arabic (MSA).We report ∼ 73\% accuracy for system combination. All the data and the code used in our experiments are publicly available for research.",
keywords = "Acoustic, Arabic, Convolutional Neural Network, Lexical, Logistic Regression, Phonotactic, Spoken Dialect Identification, Support Vector Machine",
author = "Sameer Khurana and Maryam Najafian and Ahmed Ali and Hanai, \{Tuka Al\} and Yonatan Belinkov and James Glass",
note = "Publisher Copyright: Copyright {\textcopyright} 2017 ISCA.; 18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017 ; Conference date: 20-08-2017 Through 24-08-2017",
year = "2017",
doi = "10.21437/Interspeech.2017-1391",
language = "الإنجليزيّة",
volume = "2017-August",
series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
pages = "2591--2595",
booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
}