Owner

etzinis

5 indexed repositories · View on GitHub

• sudo_rm_rf

  Code for SuDoRm-Rf networks for efficient audio source separation. SuDoRm-Rf stands for SUccessive DOwnsampling and Resampling of Multi-R...

  Jupyter Notebook · 338 stars

• two_step_mask_learning

  A two step optimization for sound source separation on the adaptive front-end domain

  Python · 70 stars

• unsup_speech_enh_adaptation

  Unsupervised domain adaptation for conversational speech enhancement using RemixIT

  Jupyter Notebook · 59 stars

• heterogeneous_separation

  Code and data recipes for the paper: Heterogeneous Target Speech Separation

  Python · 44 stars

• activelearning

  Active Learning for Emotionally Salient Utterances and Segments using Text & Audio

  Python · 4 stars