Conditioned Source Separation for Music Instrument Performances
arXiv:2004.03873 · doi:10.1109/TASLP.2021.3082331
Abstract
In music source separation, the number of sources may vary for each piece and some of the sources may belong to the same family of instruments, thus sharing timbral characteristics and making the sources more correlated. This leads to additional challenges in the source separation problem. This paper proposes a source separation method for multiple musical instruments sounding simultaneously and explores how much additional information apart from the audio stream can lift the quality of source separation. We explore conditioning techniques at different levels of a primary source separation network and utilize two extra modalities of data, namely presence or absence of instruments in the mixture, and the corresponding video stream data.
arXiv comment14 pages, 5 figures, under review
References in corpus (5)
- Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation
- Creating A Multi-track Classical Musical Performance Dataset for Multimodal Music Analysis: Challenges, Insights, and Applications
- Improving Universal Sound Separation Using Sound Classification
- Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision
- Conditioned-U-Net: Introducing a Control Mechanism in the U-Net for Multiple Source Separations