QMDIS

QCRI-MIT advanced dialect identification system

Sameer Khurana, Maryam Najafian, Ahmed Ali, Tuka Al Hanai, Yonatan Belinkov, James Glass

Research output: Contribution to journalConference article

6 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)2591-2595
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2017-August
DOIs
Publication statusPublished - 1 Jan 2017

Fingerprint

System Identification
Identification (control systems)
Logistic Regression
Continuation
Experiment
Support vector machines
Logistics
Support Vector Machine
Acoustics
Classifiers
Experiments
Classifier
Neural Networks
Neural networks

Keywords

  • Acoustic
  • Arabic
  • Convolutional Neural Network
  • Lexical
  • Logistic Regression
  • Phonotactic
  • Spoken Dialect Identification
  • Support Vector Machine

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Cite this

QMDIS : QCRI-MIT advanced dialect identification system. / Khurana, Sameer; Najafian, Maryam; Ali, Ahmed; Hanai, Tuka Al; Belinkov, Yonatan; Glass, James.

In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2017-August, 01.01.2017, p. 2591-2595.

Research output: Contribution to journalConference article

Khurana, Sameer ; Najafian, Maryam ; Ali, Ahmed ; Hanai, Tuka Al ; Belinkov, Yonatan ; Glass, James. / QMDIS : QCRI-MIT advanced dialect identification system. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2017 ; Vol. 2017-August. pp. 2591-2595.
@article{272a059374a64d6daedd618f918cc40d,
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",
year = "2017",
month = "1",
day = "1",
doi = "10.21437/Interspeech.2017-1391",
language = "English",
volume = "2017-August",
pages = "2591--2595",
journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
issn = "2308-457X",

}

TY - JOUR

T1 - QMDIS

T2 - QCRI-MIT advanced dialect identification system

AU - Khurana, Sameer

AU - Najafian, Maryam

AU - Ali, Ahmed

AU - Hanai, Tuka Al

AU - Belinkov, Yonatan

AU - Glass, James

PY - 2017/1/1

Y1 - 2017/1/1

N2 - 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.

AB - 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.

KW - Acoustic

KW - Arabic

KW - Convolutional Neural Network

KW - Lexical

KW - Logistic Regression

KW - Phonotactic

KW - Spoken Dialect Identification

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=85039174150&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85039174150&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2017-1391

DO - 10.21437/Interspeech.2017-1391

M3 - Conference article

VL - 2017-August

SP - 2591

EP - 2595

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SN - 2308-457X

ER -