The voice recognition module 12 executes voice recognition processing about the plurality of received recorded data (Step T2). Specifically, in the voice recognition processing, the contents of a final user's speech are interpreted while performing weighting according to the recording state information in voice-recognizing the plurality of recorded data.

Next, the voice assistant module 13 executes output destination device selection processing of selecting the device outputting the voice assistant from the plurality of devices 20 (Step T3). Specifically, in the output destination device selection processing, the device outputting the voice assistant among the plurality of devices 20 is selected according to a predetermined priority with reference to the usage state information received from the plurality of devices 20 and the corresponding device information (the type and the specification of the output units mounted on the devices 20) registered in the storage module 14. The device outputting the voice assistant is not limited to the device sending out the recorded data and the other devices may be selected.

The voice assistant module 13 executes the voice assistant using the selected device 20 as the output destination (Step T4). The selected device outputs the voice assistant (Step S5).