Documents
Poster
Poster
End-to-End Sound Source Separation Conditioned On Instrument Labels
- Citation Author(s):
- Submitted by:
- Olga Slizovskaia
- Last updated:
- 10 May 2019 - 7:16am
- Document Type:
- Poster
- Document Year:
- 2019
- Event:
- Presenters:
- Olga Slizovskaia
- Paper Code:
- AASP-P2.10
- Categories:
- Log in to post comments
Can we perform an end-to-end music source separation with a variable number of sources using a deep learning model? We present an extension of the Wave-U-Net model which allows end-to-end monaural source separation with a non-fixed number of sources. Furthermore, we propose multiplicative conditioning with instrument labels at the bottleneck of the Wave-U-Net and show its effect on the separation results. This approach leads to other types of conditioning such as audio-visual source separation and score-informed source separation.
ICASSP2019.pdf
ICASSP2019.pdf (334)