School of Computing and Informatics Technology (CIT)

Permanent URI for this community

http://10.29.1.53:4000/handle/10570/37

Browse

Browsing School of Computing and Informatics Technology (CIT) by Author "Abigaba, Wilson"
  • Item
    A framework for detecting and transcribing multilingual speech in low resource languages
    (Makerere University, 2025) Abigaba, Wilson
    This dissertation presents the development and evaluation of a novel multilingual automatic speech recognition (ASR) framework specifically designed for low-resource Ugandan languages, with focus on Luganda and Runyankole-Rukiga. The research addresses a critical gap in language technology by creating the first deep learning-based ASR system capable of transcribing speech in these Bantu languages, which collectively serve over 8 million speakers in Uganda but have historically been underrepresented in speech recognition technologies. The study employed transfer learning techniques by fine-tuning OpenAI's Whisper model on a custom-curated dataset of 2,000 speech samples comprising approximately 12 hours of audio data. The developed framework achieved a Word Error Rate (WER) of 50% for Luganda and 60% for Runyankole-Rukiga, with corresponding Character Error Rates (CER) of 22% and 28% respectively. These results represent significant improvements over baseline models, demonstrating WER reductions of up to 45% compared to non-fine-tuned systems. The framework incorporates a language detection module capable of identifying language switches with 78% accuracy, enabling real-time multilingual transcription scenarios common in Uganda's multilingual contexts. A comprehensive evaluation involving both technical benchmarks and user studies with 20 participants validated the framework's effectiveness, efficiency, and usability. The system achieved a System Usability Scale (SUS) score of 76.5, indicating above-average usability, with users rating transcription quality at 4.1 out of 5 stars. Performance analysis revealed that the model handles various acoustic conditions, speaker demographics, and speech rates with reasonable accuracy of 78.5%, though challenges remain with highly code-switched utterances and low-frequency vocabulary. The research makes several key contributions to the field of low-resource language processing: (1) creation of the first Whisper-based ASR system for Luganda and Runyankole-Rukiga; (2) demonstration of effective transfer learning strategies for Bantu languages; and (3) validation of practical deployment approaches for resource-constrained environments. The framework is designed with scalability in mind, providing a foundation for expansion to additional Ugandan languages and similar low-resource contexts across Africa. This work has significant implications for linguistic preservation, digital inclusion, and practical applications in healthcare, education, and government services within Uganda. By enabling speech-based interfaces in local languages, the framework contributes to bridging the digital divide and preserving cultural identity in an increasingly AI-driven world. Future work will focus on expanding the dataset, incorporating more speakers and dialects, implementing full code-switching detection capabilities, and deploying the system in real-world applications. Keywords: Automatic Speech Recognition, Low-Resource Languages, Multilingual ASR, Luganda, Runyankole-Rukiga, Transfer Learning, Whisper, Bantu Languages, Language Technology, Uganda
  • Item
    Internet monitoring and control application
    ( 2007-06) Abigaba, Wilson ; Ssekagya, Paul ; Atugonza, Martin ; Pajje, Emmanuel ; Kimbugwe, Nasser ; Mirembe, Irene Kawuta ; Katumba, Elvis Hues ; Kisitu, Kwesiga Samuel
    With the advent of the Internet and network technology, many organizations are now being equipped with Internet connections, either through wired connections or wireless infrastructure. Internet access provides students and staff an additional source from which to obtain course-related information. However, Internet misuse can be a distraction. This distraction could potentially cause poor staff and student performance levels. Network administrators need a mechanism to control how students and staff access the Internet. There is also a need to move from time wasting and cumbersome methods of managing resource usage on LANs. To fulfill these needs, we propose a web based Internet Monitoring and Control Application. This project describes a web-based application that can be used to monitor and control Internet usage on a LAN. The Internet Monitoring and Control Application (IMCA) is an application that logs all user Internet access, generates actionable knowledge that can be used for management and control purposes and generally streamlines Internet usage at CIT. IMCA includes modules for real-time alerting and report generation that are specifically designed to improve system administration functions. The application will avail users (in particular the Systems Administrator) with timely and online access to information related to Internet usage. The IMCA is designed to be easily deployed and the simple and intuitive web-based control interface provides a user-friendly configuration interface for the Systems Administrator. Through this powerful yet flexible interface, the Systems Administrator or Network Administrator can easily set Internet access rules and thus exercise control.