End-to-End Sound Source Separation Conditioned On Instrument Labels
This work addresses music source separation for audio processing applications, presenting an incremental improvement with novel conditioning.
The authors tackled the problem of end-to-end music source separation with a variable number of sources by extending the Wave-U-Net model and introducing multiplicative conditioning with instrument labels at the bottleneck, which improved separation results and enabled other conditioning types like audio-visual and score-informed separation.
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.