search

yxlu-0102 / MP-SENet

MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra
MIT License
267 stars 40 forks source link

Real-time or causal system #4

Closed rohithmars closed 3 months ago

rohithmars commented 11 months ago

Hello,

Thanks for releasing the code and other details.

Is the MP-SENet model causal? Is it possible to use it for real-time speech enhancement?

yxlu-0102 commented 11 months ago

The MP-SENet model is non-causal and has latency. We attempted to use causal convolutions for phase prediction in other work, but employed additional knowledge distillation.