The Python audio processing suite is a module that contains a variety of convenience functions to process audio signals. It can be used to plot spectral analyses of a song across time and to quickly ascertain encoding quality, but the instrumental goal of this suite is to robustly identify duplicated songs, regardless of which album they were released in, encoding quality, or start time.
| Tags | Software Development Libraries Python Modules Scientific/Engineering Visualization Mathematics multimedia Sound/Audio Analysis |
|---|---|
| Licenses | GPLv3 |
| Operating Systems | POSIX Linux |
| Implementation | Python |
Recent releases


Release Notes: The code has been reorganized into separate sub-modules. A streaming model has been implemented that does not require decoding of the entire file and does not use temporary files. Song analysis performance has been boosted by 2x with the streaming model.


Release Notes: The default parameters were tuned for optimum correlation coefficients. The library was cleaned up, splitting graphing into a separate workbench module. More options were added to the command-line programs. Some functions were documented, and some bugs were fixed. The API remains unchanged, but it will change in the future.


Release Notes: The command line interface to the library was enhanced. A series of bugs in it was fixed. Performance was enhanced. The ability to plot the sound visually was developed.


No changes have been submitted for this release.