NAIROBI, Kenya, Feb 12 – Microsoft Research has launched Paza, a new initiative aimed at advancing automatic speech recognition (ASR) for low-resource African languages, in a bid to expand equitable access to digital technology.
At the centre of the programme is PazaBench, the first evaluation platform dedicated to low-resource languages. The benchmark covers 39 African languages and evaluates 52 speech and language models, including newly released Paza ASR models for six Kenyan languages.
“Language should not be a barrier to access in the digital age,” said Mercy Muchai, Research Engineer II and one of the project leads.
“With Paza, we are co-creating speech technology with the communities who use it, ensuring that the voices of speakers of low-resource languages are heard, understood, and meaningfully included.”
The initiative has also introduced fine-tuned ASR models optimised for Swahili and Kenyan languages including Dholuo, Kalenjin, Kikuyu, Maasai and Somali.
“Real-world speech recognition must work for everyone, not just a few widely spoken languages,” said Kevin Chege, Machine Learning Engineer on the project, noting that models were tested in low-bandwidth and noisy environments to reflect everyday usage conditions.
