Documents
Presentation Slides
Presentation Slides
Unsuper vised Deep Clustering for Source Separation: Direct Learning from Mixtures Using Spatial Information Slides
![](https://sigport.org/sites/default/files/styles/home/public/ICASSP_2019_0.jpg?itok=OnlvXQeZ)
- Citation Author(s):
- Submitted by:
- Efthymios Tzinis
- Last updated:
- 7 May 2019 - 4:28pm
- Document Type:
- Presentation Slides
- Document Year:
- 2019
- Event:
- Presenters:
- Efthymios Tzinis
- Paper Code:
- AASP-L3.5
- Categories:
- Log in to post comments
We present a monophonic source separation system that is trained by only observing mixtures with no ground truth separation information. We use a deep clustering approach which trains on multi-channel mixtures and learns to project spectrogram bins to source clusters that correlate with various spatial features. We show that using such a training process we can obtain separation performance that is as good as making use of ground truth separation information. Once trained, this system is capable of performing sound separation on monophonic inputs, despite having learned how to do so using multi-channel recordings.