3 papers
eess.AS2020
Unsupervised Interpretable Representation Learning for Singing Voice Separation
Stylianos I. Mimilakis, Konstantinos Drossos, Gerald Schuller
In this work, we present a method for learning interpretable music signal representations directly from waveform signals. Our method can be trained using unsupervised objectives an…
eess.AS2019
Examining the Mapping Functions of Denoising Autoencoders in Singing Voice Separation
Stylianos Ioannis Mimilakis, Konstantinos Drossos, Estefanía Cano +1
The goal of this work is to investigate what singing voice separation approaches based on neural networks learn from the data. We examine the mapping functions of neural networks b…
cs.SD2017
Investigating the Potential of Pseudo Quadrature Mirror Filter-Banks in Music Source Separation Tasks
Stylianos Ioannis Mimilakis, Gerald Schuller
Estimating audio and musical signals from single channel mixtures often, if not always, involves a transformation of the mixture signal to the time-frequency (T-F) domain in which…