Skip to main content
  • Get to know the dedicated professionals behind our success
Alexander Kivaisi

Alexander Rogath Kivaisi

College of Information and Communication Technologies

Computer Science and Engineering

Biography

Dr. Alexander Rogath Kivaisi is a Lecturer at the University of Dar es Salaam, in the College of Information and Communication Technologies, Department of Computer Science and Engineering (CSE), where he has been contributing to both teaching and research since 2024. He holds a Bachelor of Science in Computer Science from the University of Dar es Salaam (2009), a Bachelor of Science (Hons) in Information Technology from the University of Cape Town (2011), and a Master of Science in Computer Science from the University of Cape Town (2015). Dr. Kivaisi completed his PhD in Computer Science and Technology at the Beijing Institute of Technology (2024), where his research focused on speech recognition systems and machine learning applications for low-resource languages, particularly Swahili.

His research contributions focus on enhancing Swahili speech recognition systems, applying machine learning techniques to low-resource languages, and improving methods for spoken word recognition and keyword spotting in noisy environments. Dr. Kivaisi’s publications delve into the development of advanced pre-training techniques, data augmentation strategies, and the application of multi-task learning to improve the performance of models for low-resource speech tasks. 

Dr. Kivaisi has led several notable projects, including the development of a comprehensive Swahili language dataset to improve speech recognition technologies for Swahili speakers, and the creation of an Android-based application designed to assist Swahili-speaking visually impaired individuals with touchscreen phones. These projects reflect his commitment to improving accessibility and advancing local language technology solutions in Tanzania and beyond.

Research Interest

Speech processing

Spoken Language Understanding

Deep learning

Low-resource languages

Contacts

Email:

Projects

Enabling Swahili visually impaired people to use touch screen phones. - 2015

Development of Spoken Swahili Dataset (University of Dar-es-Salaam) - 2020 – 2021

Publications

Alexander Kivaisi and Audrey Mbogho, “Web-Based Acquisition for Swahili Language Modelling”, SLTU, 2012. 

Alexander R. Kivaisi, Qingjie Zhao and Jimmy T. Mbelwa. Swahili Speech Dataset Development and Improved Pre-training Method for Spoken Digit Recognition [J]. ACM Transactions on Asian and Low-Resource Language Information Processing, 2023, 22(7) : 1-24. 

Alexander Rogath Kivaisi, Qingjie Zhao and Yuanbing Zou. Multi-task Convmixer Networks with Triplet Attention for Low-Resource Keyword Spotting [J]. Tsinghua Science and Technology, 2024.

Alexander Rogath Kivaisi and Qingjie Zhao. Improved Mini-batch Multiple Augmentation for Low- Resource Spoken Word Recognition [J]. Expert Systems With Applications, 252, 2024, 124157.