liduojia commited on
Commit
c958a64
·
verified ·
1 Parent(s): f108b12

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -1,3 +1,8 @@
 
 
 
 
 
1
  # MeanFlowSE — One-Step Generative Speech Enhancement
2
 
3
  **MeanFlowSE** is a conditional generative approach to speech enhancement that learns average velocities over short time spans and performs enhancement in a single step. Instead of rolling out a long ODE trajectory, it applies one backward-in-time displacement directly in the complex STFT domain, delivering competitive quality at a fraction of the compute and latency. The model is trained end-to-end with a local JVP-based objective and remains consistent with conditional flow matching on the diagonal—no teacher models, schedulers, or distillation required. In practice, 1-NFE inference makes real-time deployment on standard hardware straightforward.
@@ -216,4 +221,4 @@ We gratefully acknowledge **Prof. Xie Chen’s group (X-LANCE Lab, SJTU)** for t
216
 
217
 
218
  **Questions or issues?** Please open a GitHub issue or pull request.
219
- We welcome contributions — from bug fixes to new backbones and front-ends.
 
1
+ ---
2
+ license: mit
3
+ datasets:
4
+ - JacobLinCool/VoiceBank-DEMAND-16k
5
+ ---
6
  # MeanFlowSE — One-Step Generative Speech Enhancement
7
 
8
  **MeanFlowSE** is a conditional generative approach to speech enhancement that learns average velocities over short time spans and performs enhancement in a single step. Instead of rolling out a long ODE trajectory, it applies one backward-in-time displacement directly in the complex STFT domain, delivering competitive quality at a fraction of the compute and latency. The model is trained end-to-end with a local JVP-based objective and remains consistent with conditional flow matching on the diagonal—no teacher models, schedulers, or distillation required. In practice, 1-NFE inference makes real-time deployment on standard hardware straightforward.
 
221
 
222
 
223
  **Questions or issues?** Please open a GitHub issue or pull request.
224
+ We welcome contributions — from bug fixes to new backbones and front-ends.