Hello Afrika: Speech Commands in Kinyarwanda
This addresses a gap in speech recognition for African languages, particularly benefiting users in Rwanda and persons with disabilities, though it is incremental as it applies existing methods to a new language.
The Hello Afrika project tackled the lack of speech command models for African languages by developing a model for Kinyarwanda, which was deployed on multiple devices and assessed with performance metrics.
Voice or Speech Commands are a subset of the broader Spoken Word Corpus of a language which are essential for non-contact control of and activation of larger AI systems in devices used in everyday life especially for persons with disabilities. Currently, there is a dearth of speech command models for African languages. The Hello Afrika project aims to address this issue and its first iteration is focused on the Kinyarwanda language since the country has shown interest in developing speech recognition technologies culminating in one of the largest datasets on Mozilla Common Voice. The model was built off a custom speech command corpus made up of general directives, numbers, and a wake word. The final model was deployed on multiple devices (PC, Mobile Phone and Edge Devices) and the performance was assessed using suitable metrics.