End-to-end music source separation: is it possible in the waveform domain?

29 Oct 2018Francesc LluísJordi PonsXavier Serra

Most of the currently successful source separation techniques use the magnitude spectrogram as input, and are therefore by default omitting part of the signal: the phase. To avoid omitting potentially useful information, we study the viability of using end-to-end models for music source separation --- which take into account all the information available in the raw audio signal, including the phase... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Music Source Separation MUSDB18 Wavenet SDR (vocals) 3.46 # 2
Music Source Separation MUSDB18 Wavenet SDR (drums) 4.60 # 2
Music Source Separation MUSDB18 Wavenet SDR (other) 0.54 # 3
Music Source Separation MUSDB18 Wavenet SDR (bass) 2.49 # 3