Distributed LCMV beamformer design by randomly permuted ADMM

Sensor placement optimization of blind source separation in a wireless acoustic sensor network via hybrid descent methods

“…It is interesting to note that the performance improvement is fairly consistent even up the case of RT=500ms. To further compare the quality improvement of the enhanced speech, Figures 4b, 5b and 6b plot the perceptual evaluation of speech quality (PESQ) [35] measure for the received and separated speech (enhanced speech). Again, the results demonstrate that the PESQ score of the proposed system is greatly improved especially for lower values of RTs.…”