An Online Solution for Localisation, Tracking and Separation of Moving Speech Sources

Abstract

The problem of separating a time varying number of speech sources in a room is difficult to solve. The challenge lies in estimating the number and the location of these speech sources. Furthermore, the tracked speech sources need to be separated. This thesis proposes a solution which utilises the Random Finite Set approach to estimate the number and location of these speech sources and subsequently separate the speech source mixture via time frequency masking.