Alibaba Open-Sources Two Speech Enhancement Models, Completing 7-Model Suite

Alibaba open-sourced two new AI speech enhancement models, completing a 7-model open-source suite covering noise, echo, and overlapping speech. FLASepformer uses linear attention to speed up separation by 1.5–2.3x, and the echo cancellation model runs at just 22ms latency.

2026-09-10 ~ 2026-09-10 · 2 related posts

• Alibaba open-sources 2 more speech enhancement models, completing a 7-model toolkit with 22ms echo cancellation — aigclink · 2026-09-10

1 near-duplicate retellings: aigclink