1
$\begingroup$

I have a wav file I want to split into frames in order to feed it into a machine learning model. The problem is that the audio has silence with some noise at some points.

My problem is that I do not want to include frames with no sound (or only noise) in my dataset.

One solution I believe is to use a model for speech recognition or something similar to do classification and see if a frame includes only silence or noise.

However, I am searching for a solution that will not rely on machine learning but mostly on signal processing techniques or some other pre-processing method.

So, how could I exclude these frames with only silence or noise?

$\endgroup$
1
$\begingroup$

First you should apply speech enhancement algorithms to remove noise from speech. Then, you should use VAD (Voice Activity Detector) to remove silence from speech.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.