Revisiting Representation Learning for Singing Voice Separation with Sinkhorn Distances

In this work we present a method for unsupervised learning of audio representations, focused on the task of singing voice separation. We build upon a previously proposed method for learning representations of time-domain music signals with a re-parameterized denoising autoencoder, extending it by using the family of Sinkhorn distances with entropic regularization. We evaluate our method on the freely available MUSDB18 dataset of professionally produced music recordings, and our results show that Sinkhorn distances with small strength of entropic regularization are marginally improving the performance of informed singing voice separation. By increasing the strength of the entropic regularization, the learned representations of the mixture signal consists of almost perfectly additive and distinctly structured sources.

READ FULL TEXT

page 5

page 10

research
03/03/2020

Unsupervised Interpretable Representation Learning for Singing Voice Separation

In this work, we present a method for learning interpretable music signa...
research
10/22/2019

Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical Energy

In recent years, deep learning has surpassed traditional approaches to t...
research
02/01/2018

MaD TwinNet: Masker-Denoiser Architecture with Twin Networks for Monaural Sound Source Separation

Monaural singing voice separation task focuses on the prediction of the ...
research
01/09/2018

Informed Group-Sparse Representation for Singing Voice Separation

Singing voice separation attempts to separate the vocal and instrumental...
research
11/29/2022

Neural Vocoder Feature Estimation for Dry Singing Voice Separation

Singing voice separation (SVS) is a task that separates singing voice au...
research
11/29/2022

jaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus

We construct a corpus of Japanese a cappella vocal ensembles (jaCappella...
research
01/29/2017

Rhythm Transcription of Polyphonic Piano Music Based on Merged-Output HMM for Multiple Voices

In a recent conference paper, we have reported a rhythm transcription me...

Please sign up or login with your details

Forgot password? Click here to reset