What are some tools and methods for detecting and removing human voice from audio?
Specific case that I am interested in is this female scream at 0:04 in this video:
https://www.youtube.com/watch?v=q_9NUGFsmfc
It's an old Slovenian TV show. I would like to have it's intro (0:00 - 1:10) for my ringtone.
But the female scream as part of a ringtone is not appropriate for many social situations.
Which is why I am interested in getting it removed.
Problem is that it overlaps with the start of the guitar riff, which I do want to keep in. So just selecting that part of the audio and deleting it is not a good solution.
I have been playing around with some functions in Audacity, but so far nothing resulted in "just remove the scream".
Thank you in advance for your suggestions and advice.
Are there any other communities that would know how to achieve this?