Optimal truncation time for matched filter array processing

Matched filter array processing (MFA) has been shown to improve the signal-to-noise (SNR) quality for array speech capture in reverberant environments. However, under non-optimum conditions, MFA processing is computationally costly, and may produce little improvement or even subjective quality degradation as compared with simple time delay compensation (TDC). Appropriate truncation of the MFA filter bank is shown to reduce the computational burden without significantly reducing the capture SNR. This work attempts to find an optimal truncation time with respect to room size, wall absorption and the number of microphones used for the system. Simulations were conducted to evaluate MFA performance as a function of truncation length as these parameters were varied in situations typical of teleconferencing applications. It was demonstrated that judicious MFA truncation allows a reduction in computation load without sacrificing capture SNR