Bonaventure Dossou & Chris Emezue will talk about Automatic Speech Recognition (ASR) in Fon & Igbo. Bonaventure & Chris join us having recently accepted the Wikimedia award for Research Paper of the Year for their work with the Masakhane NLP community:|
Language is inherent & compulsory for human communication. Whether expressed written, spoken or signed, language ensures understanding between people of the same & different regions. African languages (over 2000) are complex & truly low-resourced. These languages receive minimal attention: the datasets required for NLP applications are difficult to discover & existing research is hard to reproduce. However, this is changing. With the growing awareness & effort to include more low-resourced languages in NLP research, African languages have recently been a major subject of research in natural language processing. The presentation is the story of the dynamic duo, Chris & Bonaventure, as they work towards tackling the NLP challenges facing African languages. The talk will cover a range of topics with a focus on the OkwuGb end-to-end speech recognition system for Fon & Igbo.
Bonaventure Dossou is a Masters's Student at Jacobs University, Bremen, & a research Intern at Mila Quebec AI Institute, working under the supervision of Professor Yoshua Bengio, & at Roche. His research areas include Machine & Deep learning (and its application in computer vision, natural language processing for Healthcare & African Languages), Computational biology, Network Science Approaches in Biology & Medicine.
Chris Emezue is a Master's student at the Technical University of Munich. He works with SIEMENS & also recently joined the Mila Quebec AI Institute as a research intern. His research areas include machine/deep learning, reinforcement learning, multilingualism, knowledge-graph representations, speech processing, & AfricaNLP.
We will add a zoom link to join on the day of the presentation.