#27 Comparison of SRP-PHAT and Multiband-PoPi Algorithms for Speaker Localization Using Particle Filters
Tania Habib and Harald Romsdorfer
The task of localizing single and multiple concurrent speakers in a reverberant environment with background noise poses several problems. One of the major problems is that frame wise localization estimates are severely corrupted in such acoustic environments. To improve the overall localization accuracy in such an acoustic setting, we propose a particle filter based tracking algorithm using the recently proposed Multiband Joint Position-Pitch (M-PoPi) localization algorithm as a frame wise likelihood estimate.To prove the performance of our approach, we tested it on real-world recordings of seven different speakers and of up to three concurrent speakers. We compared this new approach with the same particle filter based tracking algorithm using the well-known SRP-PHAT algorithm as frame wise likelihood estimates. Finally, we compared both particle filter based tracking algorithms with their frame wise localization algorithms. The M-PoPi based particle filter tracking algorithm clearly outperforms the SRP-PHAT based particle filter tracking algorithm. The comparison with their frame wise localization algorithms shows that this improved performance mainly stems from the more robust M-PoPi frame wise localization estimate.