search

madhavmk / Noise2Noise-audio_denoising_without_clean_training_data

Source code for the paper titled "Speech Denoising without Clean Training Data: a Noise2Noise Approach". Paper accepted at the INTERSPEECH 2021 conference. This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples.
MIT License
172 stars 42 forks source link

Added description on how to create the virtual environment #4

Open baabakk opened 2 years ago

baabakk commented 2 years ago

The description is needed to avoid the headache caused by Microsoft Visual Studio changes and package installation fails.

baabakk commented 2 years ago

@madhavmk Take a look at this please!

madhavmk commented 2 years ago

Hello @geniusbabak. Thanks for your contribution!

I believe that the requirement is for "Microsoft Visual C++ 14.0", not "Visual Studio 2019". And besides, this seems to be a requirement only on Windows. Could you check if "Microsoft Visual C++ 14.0" is required on Linux systems as well?

Please modify the PR to describe if this is a Windows/Linux requirement accordingly.