Komar Research Center and Computer Engineering Department holds a seminar for Dr Abdulbasit Al-Talabni on automatic recognition of Kurdish dialects and language.
Dialect recognition is one of the hottest topics in the speech analysis area. In this study, a system for dialect and language recognition is developed using phonetic and style-based features. The study suggests a new set of features using one-dimensional local binary pattern (LBP). The results show that the proposed LBP set of the feature is useful to improve dialect and language recognition accuracy. The acquired data involved in this study are three Kurdish dialects (Sorani, Badini, and Hawrami) with three neighbor languages (Arabic, Persian, and Turkish). The study proposed a new method to interpret the closeness of the Kurdish dialects and their neighbor languages using confusion matrix and a non-metric multi-dimensional visualization technique. The result shows that the Kurdish dialects can be clustered and linearly separated from the neighbor languages.
About the speaker
Abdulbasit Al-Talabani received a BSc degree in Mathematics from the University of Salahadin-Erbil, Kurdistan, Iraq, in 2000 and MSc in Computer Science from Koya University, Kurdistan, Iraq in 2006 and Ph.D. in Computer Science from The University of Buckingham, UK, in 2015. In 2006 he joined the Software Engineering Department at Koya University as an Assistant Lecturer and later as a lecturer until now.