matiiin

wrong results of main_DNN_Spectral_Mapping.py

1

why the main_DNN_Spectral_Mapping.py code has a wrong results and does not enhance speech?

How and where do you use Estnoise_ms.py function? Do you detect and estimate the type and amount of noise in test stage? Based on classification or other way?

How can noise be added randomly (Initial random) in generate_timit_merged_noisy.py code?

do you have TF-Grid net code?

1

as you compared with TF-Grid net method.. did you simulate it? i want train and test it with my dataset