About Me

I am a PhD student in Computer Science at Maseno University, Kenya, and an NLP researcher at the Maseno Centre for Applied Artificial Intelligence (MCAAI). My PhD research focuses on typologically-informed automatic speech recognition (ASR) modelling.

I hold a Google Africa PhD Fellowship in Natural Language Processing (2025–2028) and a DSA Visiting Researcher Fellowship at Sunbird AI. I am a co-founder and Head of Data at Tonative Africa, and a member of the Caribou Digital Pan-African Women PhD Scholars Collective in AI & Livelihoods. My work spans dataset curation, ASR fine-tuning, misinformation modelling, and community-centred data licensing for African languages.

Research Areas

  • ASR icon

    Automatic Speech Recognition

    Typologically-informed ASR for African languages.

    PhD Research
  • NLP icon

    Natural Language Processing

    Misinformation classification in code-switched Swahili-English. Topic modelling, text classification and language modelling for low-resource African languages.

    MCAAI
  • Dataset icon

    Dataset Curation & Data Governance

    Led collection of 3,000+ hours of speech across five Kenyan languages (African Next Voices, Gates Foundation). Co-designed an Afro-centric community data licence under Mozilla Common Voice.

    KenCorpus · Tonative Africa
  • Policy icon

    AI Policy & Digital Inclusion

    Research on leveraging language technologies for inclusive access to digital government services. Community-based focus groups on eGovernance accessibility.

    Caribou Digital

Awards & Fellowships

  • 2025 Google Africa PhD Fellowship in Natural Language Processing (2025–2028)
  • 2025 DSA Visiting Researcher Fellowship at Sunbird AI, Data Science Africa (2025–2026)
  • 2025 Alele-Williams Masters Award — Deep Learning Indaba, August 2025
  • 2025 Caribou Digital Pan-African Scholars Collective — Caribou Digital & Mastercard Foundation (May 2025–June 2026)
  • 2024 Best Application for AI in Education — KAPS / Inter-University Hackathon, November 2024
  • 2023–24 Top Poster Award — Deep Learning Indaba 2023 and 2024
  • 2020 Partial MSc Scholarship — Maseno University (Oct 2020–Aug 2024)

Resume

Education

  1. PhD in Computer Science

    January 2025 — Present

    Maseno University, Kenya
    Typologically-informed ASR modelling for structurally rich, low-resource African languages.
    Google Africa PhD Fellowship in NLP (2025–2028)

  2. MSc in Computer Science

    September 2021 — November 2024

    Maseno University, Kenya (Awarded: 06/12/2024)
    Thesis: Modelling Misinformation in Swahili-English Code-switched Texts
    doi:10.5815/ijitcs.2025.01.05

  3. BSc in Computer Science

    August 2015 — December 2019

    Maseno University, Kenya — First Class Honours

Experience

  1. AI/NLP Researcher

    June 2024 — Present · Maseno Centre for Applied Artificial Intelligence (MCAAI)

    NLP for low-resource African languages, topic modelling, and lab administration. ASR for Kenyan languages. Curated PolitiKweli dataset and built a transformer-based misinformation classification model. Mentored undergraduate and postgraduate students on research and publication.

  2. Co-Founder & Head of Data

    March 2025 — Present · Tonative Africa (Remote)

    Administration, project management, and community-led extension of African datasets for context-specific ML tasks. Experimented with textual data across low-resource languages including Dholuo, Igbo, Nigerian Pidgin, Kalenjin, Kikuyu, Swahili, and Yoruba.

  3. PhD Scholar

    March 2025 — Present · Caribou Digital Pan-African Scholars Collective (Remote)

    Policy research on leveraging language technologies and AI-driven insights for inclusive access to digital government services. Designed and led community-based focus groups on accessibility of eGovernance service portals.

  4. DSA Visiting Researcher Fellow

    2025–2026 · Sunbird AI / Data Science Africa

    Developing robust, scalable ASR models for Kenyan languages using the African Next Voices dataset (3,000+ hours across Dholuo, Kikuyu, Kalenjin, Maasai, and Somali). Bridging research to production-ready speech technology.

  5. Technical Researcher

    July 2024 — Present · KenCorpus (Remote)

    Dataset curation and project management for the African Next Voices: Pilot Data Collection in Kenya and Mozilla Common Voice: Alternative Data Licensing projects. Collected 500,000+ sentences and led a team to collect 3,000 hours of audio across five Kenyan languages. Led development of an Afro-centric community data licence.

  6. Systems Support Specialist

    November 2020 — Present · Maseno University

    Microsoft Dynamics 365 ERP design and user support. Microsoft Windows Server 2019 and Microsoft Azure management and technical support.

Appointments & Service

  1. Awards Committee Member

    Deep Learning Indaba 2026

  2. Co-Publicity Chair, AbjadNLP Workshop

    COLING 2025 · EACL 2026

    Low-resource NLP workshop co-located with major computational linguistics venues.

  3. Local Organising Committee Lead

    Deep Learning IndabaX Kenya 2025

  4. KenyaNLP Working Group Member

    Ongoing

    Contributing to NLP research coordination for Kenyan languages.

  5. NeurIPS Peer Reviewer

    2025–2026

Technical Skills & Languages

  • Programming
    Python, C/C++, Java, JavaScript
  • NLP & Speech Processing
    PyTorch, TensorFlow, HuggingFace, Kaldi, Whisper
  • Machine Learning
    Transformer fine-tuning (LoRA), SSL encoders, text classification
  • Data Science
    Dataset curation, annotation pipelines, corpus design
  • Research & Writing
    LaTeX, systematic literature review, academic publication
  • Systems Administration
    Microsoft Dynamics 365, Azure, Windows Server 2019
Languages
Dholuo — Native English — Fluent Kiswahili — Fluent French — Beginner

News & Events

  • Jul 2026

    Attending AAIAC 2026 — 2nd International Conference on the Advancements of AI in the African Context

    Dar es Salaam, Tanzania · 22–23 July 2026. Conference theme: Artificial Intelligence for Inclusive and Sustainable Digital Economy in Africa.

  • 2026

    Service Awards Committee Member — Deep Learning Indaba 2026

    Serving on the awards committee for the 2026 edition of Deep Learning Indaba, Africa's largest gathering for ML and AI research.

  • May 2026

    Paper Presented AfriVoices-KE at LREC-SIGUL 2026

    Palma de Mallorca, Spain · 11–16 May 2026. Presented AfriVoices-KE: A Multilingual Speech Dataset for Kenyan Languages at the SIGUL 2026 Joint Workshop co-located with LREC 2026. arXiv:2604.08448 ↗

  • Apr 2026

    Paper CHI EA 2026 — AI Across Cultures Workshop

    Co-authored AI Across Cultures: Co-Designing Equitable and Culturally Grounded Futures, presented at the ACM CHI 2026 Extended Abstracts.

  • Jan 2026

    Service AbjadNLP Workshop Co-Publicity Chair at EACL 2026

    Continued co-chairing publicity for the AbjadNLP low-resource NLP workshop, co-located with EACL 2026.

  • Aug 2025

    Award Alele-Williams Masters Award — Deep Learning Indaba 2025

    Received the Alele-Williams Masters Award at Deep Learning Indaba 2025, recognising outstanding MSc-level research in African ML.

  • 2025

    Fellowship Google Africa PhD Fellowship in NLP (2025–2028)

    Awarded the Google Africa PhD Fellowship in Natural Language Processing to support PhD research on typologically-informed ASR for low-resource Kenyan languages.

  • 2025

    Fellowship DSA Visiting Researcher Fellowship at Sunbird AI

    Awarded a Data Science Africa Visiting Fellowship hosted at Sunbird AI (Uganda), focused on building production-ready ASR models for Kenyan languages using the AfriVoices-KE dataset.

  • Jan 2025

    Service AbjadNLP Workshop Co-Publicity Chair at COLING 2025

    Co-chaired publicity for the AbjadNLP Workshop on low-resource NLP, co-located with COLING 2025.

  • Nov 2024

    Award Best Application for AI in Education — KAPS Hackathon

    Won Best Application for AI in Education at the KAPS / Inter-University Hackathon, November 2024.

  • Sept 2024

    Award Top Poster Award — Deep Learning Indaba 2024

    Recognised with a Top Poster Award at Deep Learning Indaba 2024.

  • Sept 2023

    Award Top Poster Award — Deep Learning Indaba 2023

    Recognised with a Top Poster Award at Deep Learning Indaba 2023 — first time attending a major international ML conference.

Publications

See also: Google Scholar · ORCID

2026

  • AfriVoices-KE: A Multilingual Speech Dataset for Kenyan Languages

    Wanzare, L., Amol, C. J., Maina, E., Odhiambo, N., et al.
    LREC-SIGUL 2026 Joint Workshop · arXiv:2604.08448

    arxiv.org/abs/2604.08448 ↗

  • AI Across Cultures: Co-Designing Equitable and Culturally Grounded Futures

    Kondoro, A. M., Farao, J., Amol, C. J., Mubiru, K. S., et al.
    CHI EA 2026 — Extended Abstracts of the ACM CHI Conference on Human Factors in Computing Systems

2025

  • Modelling Misinformation in Swahili-English Code-switched Texts

    Amol, C. J., Wanzare, L., & Obuhuma, J.
    International Journal of Information Technology and Computer Science (IJITCS)

    doi:10.5815/ijitcs.2025.01.05 ↗

  • Proceedings of the AbjadNLP Workshop

    El-Haj, M., Haddad, A., Amol, C. J., Ahmadi, S., Paterson III, H., Ezeani, I., & Rayson, P.
    The 31st International Conference on Computational Linguistics (COLING 2025)

2024

  • State of NLP in Kenya: A Survey

    Amol, C. J., Chimoto, E. A., Gesicho, R. D., Gitau, A. M., Etori, N. A., Wanzare, L. D. A., et al.
    arXiv preprint · arXiv:2410.09948

    arxiv.org/abs/2410.09948 ↗

2023

  • PolitiKweli: A Swahili-English Code-switched Twitter Political Misinformation Classification Dataset

    Amol, C. J., Wanzare, L., & Obuhuma, J.
    SPELLL 2023 · Speech and Language Technologies for Low-resource Languages, pp. 3–17, Springer

In Progress

  • The Digital Revolution: Leveraging Language Technologies for Inclusive Access to Digital Government Services for the Youth

    Amol, C. J.