Unsupervised Speech Separation Using Mixtures of Mixtures

Efthymios Tzinis
Efthymios Tzinis
Hakan Erdogan
Hakan Erdogan
John R Hershey
John R Hershey

2020.

Cited by: 0|Bibtex|Views11

Abstract:

Supervised approaches to single-channel speech separation rely on synthetic mixtures, so that the individual sources can be used as targets. Good performance depends upon how well the synthetic mixture data match real mixtures. However, matching synthetic data to the acoustic properties and distribution of sounds in a target domain can be...More

Code:

Data:

Your rating :
0

 

Tags
Comments