3 citations · 11 across the 7 of their papers we have counts for
7 papers
Proceedings of the NeurIPS 2021 Workshop on Machine Learning for the Developing World: Global Challenges
Paula Rodriguez Diaz, Tejumade Afonja, Konstantin Klemmer +4
These are the proceedings of the 5th workshop on Machine Learning for the Developing World (ML4D), held as part of the Thirty-fifth Conference on Neural Information Processing Syst…
Learning Nigerian accent embeddings from speech: preliminary results based on SautiDB-Naija corpus
Tejumade Afonja, Oladimeji Mudele, Iroro Orife +6
This paper describes foundational efforts with SautiDB-Naija, a novel corpus of non-native (L2) Nigerian English speech. We describe how the corpus was created and curated as well…
Proceedings of the NeurIPS 2020 Workshop on Machine Learning for the Developing World: Improving Resilience
Tejumade Afonja, Konstantin Klemmer, Aya Salama +3
These are the proceedings of the 4th workshop on Machine Learning for the Developing World (ML4D), held as part of the Thirty-fourth Conference on Neural Information Processing Sys…
Differentiable Histogram with Hard-Binning
Ibrahim Yusuf, George Igwegbe, Oluwafemi Azeez
The simplicity and expressiveness of a histogram render it a useful feature in different contexts including deep learning. Although the process of computing a histogram is non-diff…
Efficient Integration of Multi-channel Information for Speaker-independent Speech Separation
Yuichiro Koyama, Oluwafemi Azeez, Bhiksha Raj
Although deep-learning-based methods have markedly improved the performance of speech separation over the past few years, it remains an open question how to integrate multi-channel…
Agent Probing Interaction Policies
Siddharth Ghiya, Oluwafemi Azeez, Brendan Miller
Reinforcement learning in a multi agent system is difficult because these systems are inherently non-stationary in nature. In such a case, identifying the type of the opposite agen…
Unsupervised Domain Adaptation by Optical Flow Augmentation in Semantic Segmentation
Oluwafemi Azeez
It is expensive to generate real-life image labels and there is a domain gap between real-life and simulated images, hence a model trained on the latter cannot adapt to the former.…