A digital sound processing system suitable for use in a vehicle comprises an interior rearview mirror assembly that includes at least a first microphone and a second microphone. The first microphone generates a first signal indicative of a vocal input with vehicle cabin noise included therewith and the second microphone generates a second signal indicative of a vocal input with vehicle cabin noise included therewith. A digital signal processor is provided that processes the first signal and the second signal and that provides an output signal with reduced vehicle cabin noise. The digital signal processor preferably comprises a microprocessor executing at least one million instructions per second.