AAU Institutional Repository (AAU-ETD)
Addis Ababa University Institutional repository is an open access repository that collects,preserves, and disseminates scholarly outputs of the university. AAU-ETD archives' collection of master's theses, doctoral dissertations and preprints showcase the wide range of academic research undertaken by AAU students over the course of the University's long history.
How to Submit Your Work
The repository contains scholarly work, both unpublished and published, by current or former AAU faculty, staff, and students, including Works by AAU students as part of their masters, doctoral, or post-doctoral research
- All AAU faculty, staff, and students are invited to submit their work to the repository. Please contact the library at your college.
You may contact digirep@aau.edu.et.with any questions about the repository
Colleges,Institutes in AAU-ETD
Select a college,institute to browse its collections.
Recent Submissions
Afaan Oromoo Audio Deepfake Detection Model Using Hybrid Deep Learning Techniques
(Addis Ababa University, 2025-05-01) Oromia Chala; Minale Ashagrie
Deepfake technology has quickly grown through advances in deep learning and generative adversarial networks, enabling the creation of highly realistic synthetic media. However, these technological breakthroughs have also raised serious alarms concerning the possible misappropriation of DF content for spreading misinformation, fraud, and voice impersonation. Despite the growing complexity of Deepfake generation, there exists a considerable disparity in developing effective and robust detection techniques for audio Deepfakes, particularly for languages such as Afaan Oromoo. As widely spoken as Afaan Oromoo is despite the richness of linguistic content, insufficient focused research and customized detection models exist that are addressed to its characteristic phonetic and prosodic features. The identified gap reveals that speakers and systems utilizing Afaan Oromoo are vulnerable to risks linked to synthetic audio, such as security vulnerabilities and the dissemination of misinformation. This thesis proposes a novel hybrid deep learning approach for audio Deepfake detection. A hybrid model that integrates Convolutional Neural Networks (CNNs) for spatial feature extraction with Long Short-Term Memory (LSTM) networks for capturing temporal dependencies is developed. A comprehensive dataset was created by collecting genuine audio from reliable source and generating synthetic audio using a real-time voice cloning (RTVC) system. Extensive experiments demonstrated that the proposed CNN-LSTM model successfully learned the subtle acoustic and prosodic characteristics of Afaan Oromoo speech, achieving a training accuracy of 97.40% and an overall test accuracy of 95% a figure that accurately reflects the model’s robust generalization performance, as opposed to the previously noted 96% accuracy. The experimental results validated through additional metrics including precision, recall, and F1-score 0.95 for both real and fake. This research contributes a tailored, language-specific hybrid deep learning model for Deepfake detection, contribution a feasible solution to mitigate the risks associated with synthetic audio in underrepresented linguistic communities
Production and Evaluation of the Biotechnological Potential of Alkaliphilic Protease from Tannery Waste Microbes
(Addis Ababa University, 2025-02-01) Yoseph Sisay; Addis Simachew
The global leather industry generates significant volumes of tannery waste, contributing to environmental degradation and public health concerns. The study investigated the production of alkaliphilic protease from tannery waste microbes, and its potential applications for detergent and leather industries were also evaluated. After the isolation of more than 100 bacterial strains and screening of 22 alkaline protease-producing bacteria, strain YATW18 has been identified as the most efficient producer of extracellular alkaline protease with 92.65 U/ml enzyme activity in 48 hours. Molecular characterization has assured the genus and species name of strain YATW18to be Alkalihalophilus pseudofirmus. The partial sequence of Alkalihalophilus pseudofirmus strain YATW18 16S rRNA gene was submitted to the NCBI database and the accession number was obtained as PP942174. Fructose as a carbon source exhibited the highest enzyme activity with an average yield of 82 2.98 U/ml, and peptone as a nitrogen source resulted in the highest enzyme activity of 96.86 2.98 U/ml. From locally available substrates, water hyacinth has demonstrated the highest alkaline protease yield of 661.85 10.98 U/g. The mean differences in optimizing parameters including carbon sources, nitrogen sources, and locally available substrates were statistically significant at P 0.05. Physicochemical characterization of alkaline protease showed optimum activity at 55 and pH 10. The enzyme reached its saturation level within 20 minutes of incubation time and then linear activity was observed until 45 minutes. Alkaliphilic protease (77.92 U/ml and 99.6 U/ml) showed high protein (egg yolk) stain removal efficiency and dehairing (goat and sheep skins) capacity
Hybridity and Cultural Sharing Of Oromo And Sodo (Kistane) Gurage Ethnic Groups
(Addis Abeba Universty, 2026) Tesfaye Kufa; Tadele Tilahun (Ass. Prof)
In this study the Oromo and Sodo (Kistane) Gurage Ethnic Groups in Ethiopia are Examined in Relation to their Exchange of Traditional Practices and the Development of Cultural Hybridity. It Looks at how Changing Interethnic Relations have Influenced Religious Rites, Marriage Traditions and Social Festivities. The Study Emphasizes how Cultural Adaptation and Exchange have Enabled Each Community to Absorb Aspects of the others Traditions Resulting in a Diverse yet Shared Set of Customs. This Approach Analyzes Anthropological Literature and Carries out in-depth Interviews with Local Seniors. The Study uses Qualitative Interviewing Besides Ethnographic Methods in Order to Collect Firsthand Accounts of Cultural Practices, Belief Systems and Daily Rituals. The Impact of Musical Hybridity Defined as Common Rhythms and Performance Styles is Highlighted as a Crucial Tool for Enhancing Intergroup Understanding. In this View Music is an Ideal Artistic Medium for the Expression of Hybrid Identities and for Conflict-Resolution in Informal Spheres like Rituals and Social Gatherings. The Results are Consistent with More Extensive Studies Showing that in Multicultural Societies Music and Cross-Cultural Interactions can Foster Iclusive Identities and Reduce Social Barriers. In the end this Study Advances Knowledge of Cultural Hybridity as an Essential Tool for Maintaining Cultural Diversity and Promoting Harmonious Coexistence in Ethiopia's Intricate Social Environment.
The Fino Instrument: A Pillar of Yem Special Woreda's Cultural Heritage
(Addis Abeba University, 2026) Atnatiyos Neway; Melaku Yigezu (Phd)
This Research will Try to Explore the Cultural and Musical Significance of Fino, a Wind Instrument of Yem People Dwelling in Yem Zone of Central Ethiopia Regional State as well as Educational Values in a Sense to Preserve the Instrument and Musical Elements. The Research will Focus on the
Historical Backgrounds, Construction and Structure of the Instrument, ways of Playing and Socio cultural Role of the Fino in the Yem Community. The Researcher Used Ethnography Type of Qualitative Research Design. The Study Reveals that Life of the Yem Community is Closely Interrelated with Fino; in One way as a Musical Instrument, another way as an Identity and Cultural Symbol Which Enables Cohesion and Persistence of Yem Identity and Continuity. Fino has Important Roles in Festivals, Weddings, Social Gatherings and Cultural Heritages of the Community.
The Materials Used for Making Fino are of Local Sources and Handed Down to Next Generations by Traditional Craftsmanship and Informally Through Master-Apprentice Relationship. Musical Analyses of Selected Pieces (Amnebo, Arma, Wogor, Yeye and Waketa) Shows Characteristic Patterns Which May Relate to Communal Nature of Performance (Repetitive Structures, Modal-Tonality and Rhythmic Free Approach) and Ritual Meanings and Symbolism Attached to Them (Rich with Cultural Information) of the Fino Music. The Fino Culture is at Risk of Being Replaced by Modern Music and Lack of Inter-Generational Transmission. However the Essence of Fino's Existence Could be Guaranteed by Documentation, Inclusion in the School Curriculum and Through Community Involvement Preservation.
Examining the Authenticity of Ethiopian Indigenous Music: A Case Study of Sileshi Demise's (Gash Abera Molla) Yamral Hagere Music Project
(Addis Abeba University, 2026) Letarik Tilahun; Aklilu Zewide(Associate Professor)
In the Case of Diverse Country Like Ethiopia, It is Difficult to Establish a Self Singular Definition as a Homogenous Culture. Music can be Considered a Solution Between a Single Self-Definition of a Culture and More Culture as Unified One. This Thesis Mainly Focused on Extracting the Authenticity of Indigenous Ethiopian Music Through the Lens of the Project of Sileshi Demise (Gash Abera Molla) 'Yamral Hagere' Music Project. Aim to Analyze how Ethiopians Identify Musically in Common. This Thesis Examines the Musical Characteristics, Elements and Structures Through a Detailed Musical Investigation of Thirteen Tracks from the Album, Evaluating how they are Aesthetically Inclusive Through Authentic Lyrical Richness and Melodic Expressions. Data were Collected from Audio Recordings, Musical Discographies and Documents, Books, also an Articles to Evaluate the Authenticity of Ethiopian Indigenous Music.
The Findings of This Thesis Shows the ‘Yamral Hagere’ Project Serves as a Counter-Archive that Preserving Material Acoustic Purism Such as Traditional String Physics Synthesizing Among the Northern Monophonic Modes with Southern Vocal Polyphony to Resist Modern Commercial Flattening. Based on These Findings, this Thesis Recommends Restructuring Higher Education Music Curricula Beyond Simple Pentatonic Reductions and Updating National Cultural Policies to Grant Full Project Autonomy to Traditional Master Practitioners.