In Uganda, radio programs are a critical mode for sharing information and reaching out to rural communities. Farmers throughout Uganda, and across Africa, rely on radio programs in their local languages to learn more about agricultural practices and to obtain important market information.
While they are extremely valuable to their target listeners (agriculturalists), the content of these programs can also be important for researchers, government, and other decision makers as they provide an important source of information on the state of the agricultural sector. However the value to these other actors can be limited by the fact that this type of data is not easily monitored or analyzed, as the data is unstructured, often in local languages, and of varying sound quality.
The objective of this competition is to build a machine learning model to identify the agricultural keyword (which may be in English or Luganda) spoken in an audio clip. The keywords relate to crops, diseases, fertilizers, herbicides or other general agricultural topics.
This solution will help researchers from Makerere University who are developing a speech recognition model to automate the process of monitoring Luganda radio programs for agriculture-related information. This solution will enable more efficient monitoring and analysis of local language radio programs, and your work can possibly open doors for this type of natural language processing tasks in other local languages across Africa and across other sectors that use radio as a means of communication.
This challenge hosted in partnership with GIZ and the FAIR Forward initiative and the Artificial Intelligence for Development Africa(AI4D-Africa) Network.
About MUK researchers (twitter.com/air_lab_muk)
Makerere Artificial Intelligence (AI) Lab is an AI and Data Science research group based at the College of Computing and Information Sciences at Makerere University. The lab specializes in the application of artificial intelligence and data science - including, for example, methods from machine learning, computer vision and predictive analytics to problems in the developing world. This work is part of a research grant from Bill and Melinda Gates Foundation which has enabled us to build Artificial Intelligence models to mine Luganda data from local village radio stations to generate timely data on crop pests and diseases in Uganda. The results are now combined with images of diseased crops provided by local farmers and used to train machine learning models and ultimately provide a holistic crop and pest disease surveillance approach.
About FAIR Forward and GIZ (toolkit-digitalisierung.de/en/fair-forward)
The “FAIR Forward – Artificial Intelligence for all” initiative promotes a more open, inclusive and sustainable approach to AI on an international level. It is implemented by the Deutsche Gesellschaft für Internationale Zusammenarbeit (GIZ) on behalf of the German Federal Ministry for Economic Cooperation and Development (BMZ). FAIR Forward seeks to improve the foundations for AI innovation and policy in five partner countries: Rwanda, Uganda, Ghana, South Africa and India. Together with our partners, we focus on three areas of action: (1) strengthen local technical know-how on AI, (2) increase access to open AI training data, (3) develop policy frameworks ready for AI.
About AI4D-Africa; Artificial Intelligence for Development-Africa Network (ai4d.ai)
AI4D-Africa is a network of excellence in AI in sub-Saharan Africa. It is aimed at strengthening and developing community, scientific and technological excellence in a range of AI-related areas. It is composed of African Artificial Intelligence researchers, practitioners and policy makers.