DeepAI AI Chat
Log In Sign Up

UTD-CRSS Submission for MGB-3 Arabic Dialect Identification: Front-end and Back-end Advancements on Broadcast Speech

by   Ahmet E. Bulut, et al.
The University of Texas at Dallas

This study presents systems submitted by the University of Texas at Dallas, Center for Robust Speech Systems (UTD-CRSS) to the MGB-3 Arabic Dialect Identification (ADI) subtask. This task is defined to discriminate between five dialects of Arabic, including Egyptian, Gulf, Levantine, North African, and Modern Standard Arabic. We develop multiple single systems with different front-end representations and back-end classifiers. At the front-end level, feature extraction methods such as Mel-frequency cepstral coefficients (MFCCs) and two types of bottleneck features (BNF) are studied for an i-Vector framework. As for the back-end level, Gaussian back-end (GB), and Generative Adversarial Networks (GANs) classifiers are applied alternately. The best submission (contrastive) is achieved for the ADI subtask with an accuracy of 76.94 Further, with a post evaluation correction in the submitted system, final accuracy is increased to 79.76 so far for the challenge on the test dataset.


page 1

page 2

page 3

page 4


Automatic Dialect Detection in Arabic Broadcast Speech

We investigate different approaches for dialect identification in Arabic...

MIT-QCRI Arabic Dialect Identification System for the 2017 Multi-Genre Broadcast Challenge

In order to successfully annotate the Arabic speech con- tent found in o...

Classifier Ensembles for Dialect and Language Variety Identification

In this paper we present ensemble-based systems for dialect and language...

An ensemble-based framework for mispronunciation detection of Arabic phonemes

Determination of mispronunciations and ensuring feedback to users are ma...

Speech Recognition Challenge in the Wild: Arabic MGB-3

This paper describes the Arabic MGB-3 Challenge - Arabic Speech Recognit...

Convolutional Neural Networks and Language Embeddings for End-to-End Dialect Recognition

Dialect identification (DID) is a special case of general language ident...