fgnt / paderbox Goto Github PK

The PyPI windows wheels are broken:

https://github.com/fgnt/paderbox/actions/runs/4385404059

paderbox=0.0.5 has windows wheels, but ValueError: 'paderbox/array/interval/util.pyx' doesn't match any files doesn't work in Linux.

paderbox=0.0.6 has no wheels and requires a compiler.

The version number on master was not bumped with the latest release (0.0.6):

Thanks a lot for sharing this, that looks really nice ! :-)

• transform_to_baseband makes complete sense. Question : did you use it as input features to DNN, does it make any difference with or without the phase corrections? I intended to try but didn't do it yet.

• About the approach for the STFT / iSTFT, in particular about the biorthogonal synthesis window.

  • I don't find the dissertation from which the equations are derived. Would it be possible to have a link to it? Or some other resources that explains the approach? It amounts to divide the time-domain synthesized signal by the sum of the overlap-added squared analysis windows right?
  • If my understanding is correct, iSTFT(STFT(x)) == x for any window and any shift. However, if the STFT is modified (which is usually the case if we are about to take the iSTFT), the use of the biorthogonal synthesis window will bring time domain amplitude modulation. Did you make any experiments to quantify those artifacts and compare them against using the constant scaling factor? Especially for bad window choices?

Cheers,

Hi, folks.

I'm researching about modulation spectrogram. I've read a bunch of articles and past implementations in Matlab, then I'm trying to code one right now in Python.

I found this repository of yours, as well as an IEEE article from your lab describing it. The article is really helpful.

I would like to know if there's any reason about removing it from your repository. It was added in this commit, but then removed and declared obsolete in this one.

Thanks in advance :)

when I try running the file pb_bss/testing/dummy_data.py ， it errors that No module named 'lazy_dataset'.

I Follow all the command mentioned in readme. But it still doesn't work. Is there any other libraries should be intalled via pip?

By the way, what does (:Could not build wheels for paderbox, which is required to install pyproject.toml-based projects
) mean?

@thequilo Do you remember, why the default is only considered for KeyError and IndexError?
When should get_by_path fail?

Here, an extension of the doctest. IMHO the last example should work.

>>> d = {'a': 'b', 'c': {'d': {'e': 'f'}, 'g': [1, [2, 3], 4]}}
...
>>> get_by_path(d, 'c.b.c', default=42)
42
>>> get_by_path(d, 'a.b.c', default=42)
Traceback (most recent call last):
...
TypeError: string indices must be integers

The leafs in a nested structure can have any type and hence any Exception could be thrown.
So I don't get, why there is an if statement.

heyo!

I saw in your README that you wrote:

There is no clear way how to cite this repository for research. However, we would be grateful if directly import from this repository if you use, e.g., the STFT. We are also fine when you copy the code as long as it remains visible where you copied the code from.

And just wanted to suggest that you add the repository to Zenodo, which would give a clear way to cite it. Happy Holidays!