Please use this identifier to cite or link to this item:
Title: Palestinian Arabic regional accent recognition.
Authors: Hanani, Abualsoud 
Basha, Hanna 
Sharaf, Yasmeen 
Taylor, Stephen 
Keywords: Accent recognition, Palestinian Arabic accents;Arabic language - Palestine - Dialects;I-vector;Gaussian mixture model;Support vector machines;Machine learning;Artificial intelligence
Issue Date: 2015
Publisher: 2015 International Conference on Speech Technology and Human-Computer Dialogue, SpeD 2015
Abstract: We attempt to automatically recognize the speaker’s accent among regional Arabic Palestinian accents from four different regions of Palestine, i.e. Jerusalem (JE), Hebron (HE), Nablus (NA) and Ramallah (RA). To achieve this goal, we applied the state of the art techniques used in speaker and language identification, namely, Gaussian Mixture Model – Universal Background Model (GMM-UBM), Gaussian Mixture Model – Support Vector Machines (GMM-SVM) and I-vector framework. All of these systems were trained and tested on speech of 200 speakers. GMM-SVM and I-vector systems outperformed the baseline GMM-UBM system. The best result (accuracy of 81.5%) was obtained by an I-vector system with 64 Gaussian components, compared to an accuracy of 73.4% achieved by human listeners on the same testing utterances.
DOI: 10.1109/SPED.2015.7343088
Appears in Collections:Fulltext Publications

Files in This Item:
File Description SizeFormat
Palestinian Arabic regional accent recognition.pdf542.62 kBAdobe PDFView/Open
Show full item record

Page view(s)

checked on Jun 27, 2024


checked on Jun 27, 2024

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.