Conference Paper Speaker Separation in Multi-Channel Environment Using Deep Learning

Liu, Conggui  ,  Liu, Conggui  ,  井上, 中順  ,  Inoue, Nakamasa  ,  篠田, 浩一  ,  Shinoda, Koichi

115 ( no. 11 )  , pp.1 - 6 , 2017-02 , Information Processing Society of Japan , 情報処理学会
This paper addresses multi-channel speaker separation based on a deep delay-and-subtraction beamformer.Deep neural network(DNN) is first applied to estimate the delay time between speakers and microphones , and thenspeakers’ speech is recovered from mixed signals by using a delay-and-subtraction algorithm. We evaluated our methodby using simulated data made from WSJCAM0 database. The proposed method achieved high precision source localization,and about 62% relative improvement on word error rate (WER) over a delay-and-sum (DS) beamformer.

Number of accesses :  

Other information