Referring again to FIG. 7B, in some embodiments the second playback device 702b and/or MPS 100 may temporarily disable (e.g., via a disable signal, as shown) the first wake word engine 770a while the second VAS 790b processes a voice input in which the second wake word was detected. Disabling the first wake word engine 770b may occur regardless of whether the first and second playback devices 702a, 702b share detected sound from any of the microphones 722 and/or are individually using some or all of the microphones 722. It may be beneficial to disable the first wake word engine 770a while the second VAS 790b processes a voice input to suppress inadvertent detection of the first wake word and prevent potentially conflicting actions and/or output by the first and/or second playback devices 702a, 702b. In some embodiments, once the second VAS 790b has completed processing of the voice input, the first wake word engine 770a may be re-enabled. Likewise, in some embodiments the first playback device 702a and/or the MPS 100 may temporarily disable the second wake word engine 770b when the first wake word engine 770a detects a wake word. Additionally or alternatively, the microphones assigned to the first or second playback device 702a, 702b may be temporarily disabled when the wake word engine of the other playback device detects its respective wake word. In some embodiments, disabling a wake-word engine may include allowing the wake-word engine to continue to monitor for wake-words but temporarily muting the audio input upstream from the spatial processor, such as by inserting zeroes in a digital input stream or silence at a low noise level such that wake-word is less or not capable of detecting wake-words while muted.
