Skip to content

Highlights

  • Pro

Organizations

@RocketScienceAbteilung @sigsep

Pinned

  1. Deep Neural Network for Speaker Count Estimation

    Python 79 26

  2. Python I/O for STEM audio files

    Python 36 8

  3. Curated list of python software and packages related to scientific research in audio

    879 123

  4. Use haptic feedback to feel the MIDI clock beat underneath your magic trackpad

    Objective-C 37

  5. List of Reproducible Audio Research Papers

    44 9

  6. Benchmark popular audio i/o packages

    Python 43 3

Contribution activity

July 2020

Created a pull request in sigsep/open-unmix-pytorch that received 2 comments

Add encoder decoder architecture

remove transforms from core spectrogram (masking) model replace STFT and ISTFT with torchaudio functionals. make sure old models still load fin…

+229 −263 2 comments

Created an issue in pytorch/audio that received 3 comments

allow to change stft default parameters from `functional.spectrogram`

Torchaudio spectrogram sets default parameters that are passed to torch.stft. Users may want to change these defaults. functional.spectrogram passi…

3 comments
1 contribution in private repositories Jul 3

Seeing something unexpected? Take a look at the GitHub profile guide.

You can’t perform that action at this time.