New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add harmonic-percussive source separation #24

Open

jurihock opened this issue Jun 18, 2022 · 1 comment

Labels

Milestone

Owner

jurihock commented Jun 18, 2022 •

edited

Loading

Extract and transpose only the harmonic signal independently from the percussive signal.

TODO:

jurihock added the enhancement label

jurihock added this to the v2 milestone

jurihock added a commit that referenced this issue


          Create basic hpss script #24

a9a91f9

Owner Author

jurihock commented Jul 4, 2022

Thoughts:

HPSS could be generally interesting for instrumental records (percussion separation) as well as vocal records (plosive separation).
Especially in case of vocal records a higher quality algorithm is required, to reduce the propagation of audible artifacts.
Single pass (and real time) processing could be problematic, since the median filter kernel size tends to be large and requires samples from the "future".

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment