Voice interactive device and utterance control method
A voice interactive device constituting an interaction system in which a plurality of voice interactive devices interact with a user, comprises a voice input unit that acquires voice uttered by a user; an information generating unit that generates user utterance information, the user utterance information being information for specifying a voice interactive device having been spoken to by the user; a transmitting/receiving unit that transmits the generated user utterance information to another voice interactive device and that receives, from the other voice interactive device, user utterance information; a determining unit that determines whether or not a response is to be made to the utterance by the user based on the generated and received user utterance information; and an interacting unit that performs interaction with the user on the basis of a result of the determination.
1. A voice interactive device provided in an interaction system in which a plurality of voice interactive devices interact with a user,
the voice interactive device comprising:
a microphone configured to acquire a voice uttered by a user;
a processor configured to:
generate user utterance information on the basis of on the acquired voice, the user utterance information being information for specifying a voice interactive device having been spoken to by the user among the plurality of voice interactive devices;
transmit the generated user utterance information to another voice interactive device and that receives, from the other voice interactive device, user utterance information generated by the voice interactive device;
determine whether or not a response is to be made to the utterance by the user on the basis of the generated and received user utterance information; and
interact with the user by responding to the user on the basis of a result of the determination.
2. The voice interactive device according to claim 1 , wherein
the microphone is configured to detect an incoming direction of voice with respect to the voice interactive device, and
the processor is configured to generate user utterance information including one of information representing the incoming direction of voice with respect to the voice interactive device and information related to sound pressure of the voice.
3. The voice interactive device according to claim 2 , wherein
the processor is configured to determine that a response is to be made to an utterance of the user when the processor determines that the voice interactive device is most directly in front of the user among the plurality of voice interactive devices.
4. The voice interactive device according to claim 2 , wherein
the processor is configured to determine that a response is to be made to an utterance of the user when the processor determines that the voice interactive device is positioned closest to the user among the plurality of voice interactive devices.
5. The voice interactive device according to claim 2 , wherein
when the processor determines that a response is to be made to an utterance of the user,
the processor is configured to continue interacting with the user until a variation amount of the incoming direction or the sound pressure of the voice exceeds a prescribed threshold.
6. The voice interactive device according to claim 5 , wherein
the processor is configured to:
transmit information representing an interaction state between the voice interactive device and the user to another voice interactive device, and
determine whether not the interaction between the other voice interactive device and the user is continuing based on the received information, and suspends the determination whether or not a response is to be made to the utterance by the user, as long as the interaction continues.
7. The voice interactive device according to claim 1 , wherein the processor is configured to:
identify a user having uttered the acquired voice;
associate an identifier of the user with the user utterance information, and
determine whether or not a response is to be made to an utterance of the user for each identified user.
8. An utterance control method performed by a voice interactive device constituting an interaction system in which a plurality of voice interactive devices interact with a user,
the utterance control method comprising:
acquiring voice uttered by the user;
generating user utterance information on the basis of the acquired voice, the user utterance information being information for specifying a voice interactive device having been spoken to by the user among the plurality of voice interactive devices;
transmitting the generated user utterance information to another voice interactive device and receiving, from the other voice interactive device, user utterance information generated by the voice interactive device;
determining whether or not a response is to be made to an utterance by the user on the basis of the generated and received user utterance information; and
performing interaction with the user on the basis of a result of the determination.
9. A non-transitory computer readable storing medium recording a computer program for causing a computer to perform the utterance control method according to claim 8 .