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.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
