8 citations · 8 across the 1 of their papers we have counts for
2 papers
eess.AS2022★ 8 cited
MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Training
Ertuğ Karamatlı, Serap Kırbız
We introduce two unsupervised source separation methods, which involve self-supervised training from single-channel two-source speech mixtures. Our first method, mixture permutatio…
cs.SD2018
Audio Source Separation Using Variational Autoencoders and Weak Class Supervision
Ertuğ Karamatlı, Ali Taylan Cemgil, Serap Kırbız
In this paper, we propose a source separation method that is trained by observing the mixtures and the class labels of the sources present in the mixture without any access to isol…