How can I speech enhancement with DNN?

I will do speech enhancement with dnn. However, I don't know anything about this subject. I will use the TIMIT corpus for audio. I will use the Noisex-92 database for noise. I found Noisex-92 noises as .m file. But I have .wav files for TIMIT. I need to extract features of speech but I don't know how to manipulate this .wav file. I would be glad if you help.

Answer 1

[David Willingham]

Hi,

Here is a reference page for Deep Learning with audio, it would be a good place to start:

https://www.mathworks.com/help/deeplearning/audio-processing-using-deep-learning.html