Frequency Domain Passive Broadband Speaker Localization using a Permutation-Free Blind Source Separation Algorithm

Traditional passive broadband source localization techniques like maximum likelihood estimation and MUSIC have shown difficulties in situations where multiple correlating source signals are interfering with each other. Blind source separation (BSS) algorithms on the other hand have demonstrated good performance in separating correlated mixture signals into independent sources. In this paper it will be shown that the performance of traditional source localization algorithms can be improved by using a permutation-free frequency domain BSS algorithm as a front end. In addition a source localization method based solely on information gained from the separated BSS solution and sensor array architecture is presented. The methodologies are illustrated in an undercomplete acoustic scenario involving 3 speech sources and a 6 element microphone array.