Microsoft Research launches Paza to boost African speech AI

Microsoft Research launches Paza to boost African speech AI
Microsoft France headquarters entrance in Issy les Moulineaux near Paris

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.