Fabian-Robert Stöter

this is better: 

add result 

would [this paper](http://ieeexplore.ieee.org/document/7362751/) be relevant here? Also there are a few deep embedded clustering implementations around. Also one in Keras: https://github.com/fferroni/DEC-Keras but I don't know if this one is well...

maybe i was mistakenly thing the onnx error message was about the `weight_norm`. After looking into #14 it might be totally unrelated. @fuzic does your branch work fine when exported...

@bmcfee @craffel Looking into this now. I'm not sure if it's related but I had some similar issues with fft precisions when torchaudio did changes some months ago....

> I'm not sure that jitting would help for bss eval. Last I checked, the bottleneck here was in computing a bunch of frame-wise least squares solutions, and that part...

I am not sure if I understand your setup. Maybe I don't really understand what the three estimates would represent? Can you explain this in more detail, please? Also, in...

> 1> besides reference, estimate, do I need to offer the noisy to the function? what do you mean by "the noisy"? 2> the input matrices are not bounded to...

I don't know what your application is, but bss_eval is not perfectly suitable to evaluate denoising applications. If you still want to do it, make sure to pass 2 signals...

> I thought it's equivalent to the bss toolbox, http://bass-db.gforge.inria.fr/bss_eval/, but with Python. Am I wrong?? yes, it is a reimplementation of these tools. So do you get different result...