A Real-Time Dereverberation Algorithm Combined with Echo Cancellation

In order to improve the output speech quality of the near-end signal collected in the real-time communication system, a reverberation suppression algorithm with low computation is proposed. Firstly, the algorithm uses the adaptive filter of the echo canceller to model the room response. Secondly, using the linear fitting method, the reverberation time is estimated according to the modeled impulse. Then, a adaptive filter is used to estimate the echo signal and thus the error signal is obtained. Finally, the spectral subtraction method is used to obtain the estimated pure signal. Experimental results validated the efficiency of the proposed algorithm. The near-end speech can be obtained with less amount of calculation comparing to other similar algorithms.