Multi-microphone correlation-based processing for robust speech recognition

A novel method of signal processing for robust speech recognition using multiple microphones is presented. The method, loosely based on the human binaural hearing system, consists of passing the speech signals detected by multiple microphones through bandpass filtering and nonlinear rectification operations, and then cross-correlating the outputs from each channel within each frequency band. These operations provide an estimate of the energy contained in the speech signal in each frequency band, as well as rejection of off-axis jamming noise sources. It is demonstrated that this method increases recognition accuracy for a multichannel signal compared with equivalent processing of a monaural signal.<>