- Recherche et sélection de publications
|
Weakly informed audio source separation
- Kilian Schulze-Forster #1, Clément Doire #2, Gaël Richard #1, Roland Badeau #1
-
| #1 |
Laboratoire traitement et communication de l'information (LTCI)
- Télécm ParisTech
- Institut Mines-Télécom
- Université Paris-Saclay
|
| #2 |
Audionamix
|
- References
- WASPAA 2019, New Paltz, New York, USA, October 2019,
- Abstract
Prior information about the target source can improve audio source separation quality but is usually not available with the necessary level of audio alignment. This has limited its usability in the past. We propose a separation model that can nevertheless exploit such weak information for the separation task while aligning it on the mixture as a byproduct using an attention mechanism. We demonstrate the capabilities of the model on a singing voice separation task exploiting artificial side information with different levels of expressiveness. Moreover, we highlight an issue with the common separation quality assessment procedure regarding parts where targets or predictions are silent and refine a previous contribution for a more complete evaluation.
- Keywords
- informed source separation, singing voice separation, weak labels, attention, separation evaluation
- Category
- Paper in proceedings
- Research Area(s)
- Engineering Sciences/Signal and Image processing
- Identifier(s)
-
Bibliographic key KSF:WASPAA-19
- Export
-
- Last update
- on september 06, 2019 by Roland Badeau
|
