Modified predator-prey particle swarm optimization based two-channel speech quality enhancement by forward blind source separation
Sofiane Fisli, Mohamed Djendi, Abderezzak Guessoum · 2018
This paper addresses the problem of acoustic noise cancellation by adaptive filtering algorithms. To solve acoustic noise reduction and speech enhancement problems, we propose a modified predator-prey particle swarm optimization (MPPPSO) to design adaptive noise canceling based on swarm intelligence heuristic search. The steady-state error of the predator-prey particle swarm optimization (PPPSO) algorithm is bad for large filters length and non-stationary input. The MPPPSO can improve the previous PPPSO algorithm when a large filter length is used. The proposed MPPPSO algorithm shows significant improvement in the system mismatch (SM) and Output signal-to-noise ratio (SNR) values. We present simulation results of the MPPPSO algorithm that confirm the superiority and good performance in comparison with the PPPSO and the normalized least mean square (NLMS) algorithm.