RLS-Based Adaptive Dereverberation Tracing Abrupt Position Change of Target Speaker
This is an incremental improvement for speech processing systems that need to handle moving speakers in reverberant environments.
The paper tackled the problem of adaptive dereverberation failing when a speaker's position changes abruptly, proposing a time-varying forgetting factor in an RLS-based method to track such changes effectively, with simulations and experiments demonstrating its advantages.
Adaptive algorithm based on multi-channel linear prediction is an effective dereverberation method balancing well between the attenuation of the long-term reverberation and the dereverberated speech quality. However, the abrupt change of the speech source position, usually caused by the shift of the speakers, forms an obstacle to the adaptive algorithm and makes it difficult to guarantee both the fast convergence speed and the optimal steady-state behavior. In this paper, the RLS-based adaptive multi-channel linear prediction method is investigated and a time-varying forgetting factor based on the relative weighted change of the adaptive filter coefficients is proposed to effectively tracing the abrupt change of the target speaker position. The advantages of the proposed scheme are demonstrated in the simulations and experiments.