LLM News

Every LLM release, update, and milestone.

Filtered by:speech-enhancement✕ clear
research

MeanFlowSE enables single-step speech enhancement by learning mean velocity fields instead of instantaneous flows

Researchers introduced MeanFlowSE, a generative speech enhancement model that eliminates the computational bottleneck of multistep inference by learning average velocity over finite intervals rather than instantaneous velocity fields. The single-step approach achieves comparable quality to multistep baselines on VoiceBank-DEMAND while requiring substantially lower computational cost and no knowledge distillation.