Publications

Research, written
from Africa.

Peer-reviewed papers, technical reports, and dataset releases from TRI AI's research initiatives.

October 16, 2025 research ACM

The Human Labour of Data Work: Capturing Cultural Diversity through World Wide Dishes

Siobhan Mackenzie Hall, Samantha Dalal, Raesetje Sefala, Foutse Yuehgoh, Aisha Alaagib et al.
June 21, 2025 research

The World Wide recipe: A community-centred framework for fine-grained data collection and regional bias operationalisation

Jabez Magomere, Shu Ishida, Tejumade Afonja, Aya Salama, Daniel Kochin et al.
September 3, 2024 research arXiv preprint

ChowNet: An Image Dataset of Nigerian Food

Tejumade Afonja, Igwegbe George
June 27, 2024 research arXiv

1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis

Sewade Ogun, Abraham T. Owodunni, Tobi Olatunji, Eniola Alese, Babatunde Oladimeji et al.
June 18, 2024 research arXiv

Performant ASR Models for Medical Entities in Accented Speech

Tejumade Afonja, Tobi Olatunji, Sewade Ogun, Naome A Etori, Abraham Owodunni et al.
December 19, 2023 research Transactions of the Association for Computational Linguistics

AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR

Tobi OlatunjiCorresponding Author, Tejumade Afonja, Aditya Yadavalli, Chris Chinenye Emezue, Sahib Singh et al.
June 2, 2023 research arXiv

AfriNames: Most ASR models “butcher” African Names

Tobi Olatunji, Tejumade Afonja, Bonaventure F. P. Dossou, Atnafu Lambebo Tonja, Chris Chinenye Emezue et al.
February 16, 2023 research

SautiDB: Nigerian Accent Dataset Collection

Afonja Tejumade, Mbataku Clinton, Malomo Ademola, Okubadejo Olumide, Francis Lawrence et al.
December 12, 2021 research Proceedings of the African NLP Workshop

Learning Nigerian accent embeddings from speech: preliminary results based on SautiDB-Naija corpus

Tejumade Afonja, Oladimeji Mudele, Iroro Orife, Kenechi Dukor, Lawrence Francis et al.
July 16, 2021 research

A survey: Robot grasping

Kenechi F Dukor, T Afonja

Research, written from Africa.

The Human Labour of Data Work: Capturing Cultural Diversity through World Wide Dishes

The World Wide recipe: A community-centred framework for fine-grained data collection and regional bias operationalisation

ChowNet: An Image Dataset of Nigerian Food

1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis

Performant ASR Models for Medical Entities in Accented Speech

AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR

AfriNames: Most ASR models “butcher” African Names

SautiDB: Nigerian Accent Dataset Collection

Learning Nigerian accent embeddings from speech: preliminary results based on SautiDB-Naija corpus

A survey: Robot grasping

The Encoder.

Research, written
from Africa.