Iterative Deep Neural Networks for Speaker-Independent Binaural Blind Speech Separation

Qingju Liu, Yong Xu, Philip JB Jackson, Wenwu Wang, Philip Coleman
2018 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
In this paper, we propose an iterative deep neural network (DNN)-based binaural source separation scheme, for recovering two concurrent speech signals in a room environment. Besides the commonly-used spectral features, the DNN also takes non-linearly wrapped binaural spatial features as input, which are refined iteratively using parameters estimated from the DNN output via a feedback loop. Different DNN structures have been tested, including a classic multilayer perception regression
more » ... e as well as a new hybrid network with both convolutional and densely-connected layers. Objective evaluations in terms of PESQ and STOI showed consistent improvement over baseline methods using traditional binaural features, especially when the hybrid DNN architecture was employed. In addition, our proposed scheme is robust to mismatches between the training and testing data. Index Terms-Deep neural network, binaural blind speech separation, spectral and spatial, iterative DNN
doi:10.1109/icassp.2018.8462603 dblp:conf/icassp/Liu0JWC18 fatcat:gjlmw2uwajbq3g4o2wre5fsedi