Filter Bank Design for Subband Adaptive Beamforming and Application to Speech Recognition

\begin{abstract} We present a new filter bank design method for subband adaptive beamforming. Filter bank design for adaptive filtering poses many problems not encountered in more traditional applications such as subband coding of speech or music. The popular class of perfect reconstruction filter banks is not well-suited for applications involving adaptive filtering because perfect reconstruction is achieved through alias cancellation, which functions correctly only if the outputs of individual subbands are \emph{not} subject to arbitrary magnitude scaling and phase shifts. In this work, we design analysis and synthesis prototypes for modulated filter banks so as to minimize each aliasing term individually. We then show that the \emph{total response error} can be driven to zero by constraining the analysis and synthesis prototypes to be \emph{Nyquist($M$)} filters. We show that the proposed filter banks are more robust for aliasing caused by adaptive beamforming than conventional methods. Furthermore, we demonstrate the effectiveness of our design technique through a set of automatic speech recognition experiments on the multi-channel, far-field speech data from the \emph{PASCAL Speech Separation Challenge}. In our system, speech signals are first transformed into the subband domain with the proposed filter banks, and thereafter the subband components are processed with a beamforming algorithm. Following beamforming, post-filtering and binary masking are performed to further enhance the speech by removing residual noise and undesired speech. The experimental results prove that our beamforming system with the proposed filter banks achieves the best recognition performance, a 39.6% word error rate (WER), with half the amount of computation of that of the conventional filter banks while the perfect reconstruction filter banks provided a 44.4% WER. \end{abstract}