Alert button
Picture for Leo Kim

Leo Kim

Alert button

End-to-End Sound Source Separation Conditioned On Instrument Labels

Nov 05, 2018
Olga Slizovskaia, Leo Kim, Gloria Haro, Emilia Gomez

Figure 1 for End-to-End Sound Source Separation Conditioned On Instrument Labels
Figure 2 for End-to-End Sound Source Separation Conditioned On Instrument Labels
Figure 3 for End-to-End Sound Source Separation Conditioned On Instrument Labels
Figure 4 for End-to-End Sound Source Separation Conditioned On Instrument Labels

Can we perform an end-to-end sound source separation (SSS) with a variable number of sources using a deep learning model? This paper presents 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 can be further extended to other types of conditioning such as audio-visual SSS and score-informed SSS.

* 5 pages, 2 figures, 2 tables 
Viaarxiv icon