• At a glance - Microsoft Research releases PazaBench and Paza automatic speech recognition models, advancing speech technology for low resource languages. • - Human-centered pipeline for low-resource languages: Built for and tested by communities, Paza is an end-to-end, continuous pipeline that elevates historically under-represented languages and makes speech models usable in real-world, low-resource contexts. • - First-of-its-kind ASR leaderboard, starting with African languages: Pazabench is the first automatic speech recognition (ASR) leaderboard for low-resource languages. • Launching with 39 African languages and 51 state-of-the-art models, it tracks three key metrics across leading public and community datasets. • - Human-centered Paza ASR models: Minimal data, fine-tuned ASR models grounded in real-world testing with farmers on everyday mobile devices, covering six Kenyan languages: Swahili, Dholuo, Kalenjin, Kikuyu, Maasai, and Somali. • According to the 2025 Microsoft AI Diffusion Report approximately one in six people globally had used a generative AI product.
Article Summaries:
- Microsoft Research has launched PazaBench, an automatic speech‑recognition (ASR) benchmark and leaderboard, and a suite of Paza ASR models aimed at low‑resource languages. PazaBench is the first ASR leaderboard for under‑represented languages, beginning with 39 African languages and 51 state‑of‑the‑art models, and tracks key performance metrics across public and community datasets. The accompanying Paza models are fine‑tuned on minimal data and evaluated by community testers on everyday mobile devices, covering six Kenyan languages (Swahili, Dholuo, Kalenjin, Kikuyu, Maasai, Somali). The initiative builds on lessons from Project Gecko, emphasizing human‑centered design, real‑world testing, and continuous improvement for low‑resource speech technology.
Sources: