Context driven device arbitration

A system comprising:

• one or more processors;
• and
• non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
• receiving a first indication that a first microphone of a first device generated first audio data representing a speech utterance;
• receiving a second indication that a second microphone of a second device generated second audio data representing the speech utterance;
• determining intent data associated with the speech utterance, the intent data indicating a request to perform an operation;
• determining, utilizing speaker identification processing performed on at least one of the first audio data or the second audio data, a user identifier of a user that provided the speech utterance, wherein performing the speaker identification processing is based at least in part on both the first microphone and the second microphone receiving the speech utterance;
• identifying account data associated with the user identifier;
• determining, based at least in part on the account data, that the user uses the first device more than the second device;
• selecting the first device to receive a command associated with the intent data based at least in part on the user identifier and the account data indicating the user uses the first device more than the second device;
• and
• sending command data corresponding to the command to the first device instead of the second device.