End-to-end music source separation: is it possible in the waveform domain?
TL
TL;DR
A Wavenet-based model is proposed and Wave-U-Net can outperform DeepConvSep, a recent spectrogram-based deep learning model, and the results confirm that waveform-based models can perform similarly (if not better) than a spectrogram/deep learning model.
Abstract
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. Although during the last decades end-to-end music source separation has been considered almost unattainable, our results confirm that waveform-based models can perform similarly (if not better) than a spectrogram-based deep learning model. Namely: a Wavenet-based model we propose and Wave-U-Net can outperform DeepConvSep, a recent spectrogram-based deep learning model.
References34 items
1
End-to-end Networks for Supervised Single-channel Speech Separation
2
Phasebook and Friends: Leveraging Discrete Representations for Source Separation
3
Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation
4
Randomly Weighted CNNs for (Music) Audio Classification
5