CPC G10L 17/22 (2013.01) [G10L 15/02 (2013.01); G10L 15/05 (2013.01); G10L 15/22 (2013.01); G10L 17/02 (2013.01); G10L 2015/223 (2013.01)] | 20 Claims |
1. A network microphone device (NMD) comprising:
a plurality of microphones;
a network interface;
one or more processors; and
a tangible, non-transitory, computer-readable medium storing instructions that, when executed by the one or more processors, cause the NMD to perform operations comprising:
detecting first sound data via at least one of the microphones;
determining, via a voice activity detection process, that the first sound data does not include voice activity;
storing the first sound data in a buffer;
after determining that the first sound data does not include voice activity, forgoing spatial processing of the first sound data;
capturing second sound data via the at least one microphone;
determining, via the voice activity detection process, that the second sound data includes voice activity;
after determining that the second sound data includes voice activity, spatially processing the second sound data using a spatial processor to produce filtered sound data;
storing the filtered sound data in the buffer;
detecting, via a wake-word engine, a wake word based on data in the buffer; and
after detecting the wake word, determining an action to be performed based on the data in the buffer.
|