Communication assistance system, communication assistance method, and communication assistance program

1 . A communication assistance system that assists audio communication among a plurality of users, the communication assistance system comprising at least one processor configured to:

detect a line of sight of a first user with respect to a screen in a real space, the screen showing a virtual space in which a plurality of user objects corresponding to the plurality of users are arranged, the virtual space being two-dimensional or three-dimensional;

detect a speech of the first user;

specify the second user as a conversation partner of the first user when the detected line of sight of the first user with respect to the screen in the real space overlaps with a user object corresponding to the second user in the virtual space and when the speech of the first user is detected;

set a group including the first user and the second user if the second user is specified as the conversation partner of the first user; and

output, to the first user, a speech voice of the second user if the second user is specified as the conversation partner of the first user and belongs to the group with a larger volume than a speech voice of the second user in a case if the second user is not specified as the conversation partner of the first user and does not belong to the group.

2 . The communication assistance system according to claim 1 , wherein

the user object corresponding to the second user is a second user object, and

the at least one processor is configured to:

detect a positional relationship between the detected line of sight of the first user in the real space and the plurality of user objects in the virtual space; and

when the second user is specified as the conversation partner of the first user, change a position of at least one of a first user object corresponding to the first user or the second user object in the virtual space so that a distance between the first user object and the second user object is shortened.

3 . The communication assistance system according to claim 1 , wherein the at least one processor is configured to:

set a group region that visually indicates a range of the group in the virtual space; and

when the first user speaks while gazing at the group region, make a first volume of a speech voice of the first user which is output to the users who belong to the group greater than a second volume of the speech voice of the first user which is output to the users who do not belong to the group.

4 . The communication assistance system according to claim 3 , wherein the at least one processor is configured to:

calculate a degree of involvement of the first user in the group based on an amount of speech made while the first user gazes at the group region; and

determine a volume of the speech voice of the second user which is output to the first user based on the degree of involvement.

5 . The communication assistance system according to claim 1 , wherein the at least one processor is configured to:

extract a characteristic of the group based on a conversation among the users who belong to the group; and

arrange, in the virtual space, display information indicating the extracted characteristic in association with the group.

6 . The communication assistance system according to claim 1 , wherein the at least one processor is configured to, in response to execution of a predetermined action by the first user who belongs to the group while the first user gazes at a region associated with a third user object corresponding to a third user who does not belong to the group, add the third user to the group.

7 . The communication assistance system according to claim 1 , wherein the at least one processor is configured to, if a fourth user who does not belong to the first group is specified as a conversation partner of the first user while the first user belongs to the first group, set a second group including the first user and the fourth user while maintaining a state where the first user belongs to the first group.

8 . The communication assistance system according to claim 1 , wherein the at least one processor is configured to:

in a case where a plurality of groups are set, recognize conversation content among the users who belong to the respective groups; and

if the conversation content recognized for a third group and the conversation content recognized for a fourth group have a predetermined relationship, merge the third group with the fourth group.

9 . The communication assistance system according to claim 1 , wherein the at least one processor is configured to arrange display information related to the line of sight of each of the users in the virtual space.

10 . The communication assistance system according to claim 1 , wherein the at least one processor is configured to:

set a group region that visually indicates a range of the group in the virtual space;

when the first user speaks while gazing at the group region, make a first volume of a speech voice of the first user which is output to the users who belong to the group greater than a second volume of the speech voice of the first user which is output to the users who do not belong to the group; and

when a third user who does not belong to the group speaks while gazing at the group region, make a third volume of a speech voice of the third user which is output to the users who belong to the group greater than a fourth volume of the speech voice of the third user which is output to the users who do not belong to the group.

11 . A communication assistance method executed by a communication assistance system including at least one processor, the communication assistance method comprising:

detecting a line of sight of a first user with respect to a screen in a real space, the screen showing a virtual space in which a plurality of user objects corresponding to a plurality of users are arranged, the virtual space being two-dimensional or three-dimensional;

detecting a speech of the first user;

specifying the second user as a conversation partner of the first user when the detected line of sight of the first user with respect to the screen in the real space overlaps with a user object corresponding to the second user in the virtual space and when the speech of the first user is detected;

setting a group including the first user and the second user if the second user is specified as the conversation partner of the first user; and

outputting, to the first user, a speech voice of the second user if the second user is specified as the conversation partner of the first user and belongs to the group with a larger volume than a speech voice of the second user in a case if the second user is not specified as the conversation partner of the first user and does not belong to the group.

12 . The communication assistance method according to claim 11 , wherein

the user object corresponding to the second user is a second user object, and

the method further comprises:

detecting a positional relationship between the detected line of sight of the first user in the real space and the plurality of user objects in the virtual space; and

when the second user is specified as the conversation partner of the first user, changing a position of at least one of a first user object corresponding to the first user or the second user object in the virtual space so that a distance between the first user object and the second user object is shortened.

13 . The communication assistance method according to claim 11 , further comprising:

setting a group region that visually indicates a range of the group in the virtual space; and

when the first user speaks while gazing at the group region, making a first volume of a speech voice of the first user which is output to the users who belong to the group greater than a second volume of the speech voice of the first user which is output to the users who do not belong to the group.

14 . The communication assistance method according to claim 11 , further comprising:

extracting a characteristic of the group based on a conversation among the users who belong to the group; and

arranging, in the virtual space, display information indicating the extracted characteristic in association with the group.

15 . The communication assistance method according to claim 11 , further comprising, in response to execution of a predetermined action by the first user who belongs to the group while the first user gazes at a region associated with a third user object corresponding to a third user who does not belong to the group, adding the third user to the group.

16 . The communication assistance method according to claim 11 , further comprising, if a fourth user who does not belong to the first group is specified as a conversation partner of the first user while the first user belongs to the first group, setting a second group including the first user and the fourth user while maintaining a state where the first user belongs to the first group.

17 . The communication assistance method according to claim 11 , further comprising:

in a case where a plurality of groups are set, recognizing conversation content among the users who belong to the respective groups; and

if the conversation content recognized for a third group and the conversation content recognized for a fourth group have a predetermined relationship, merging the third group with the fourth group.

18 . The communication assistance method according to claim 11 , further comprising:

setting a group region that visually indicates a range of the group in the virtual space;

when the first user speaks while gazing at the group region, making a first volume of a speech voice of the first user which is output to the users who belong to the group greater than a second volume of the speech voice of the first user which is output to the users who do not belong to the group; and

when a third user who does not belong to the group speaks while gazing at the group region, making a third volume of a speech voice of the third user which is output to the users who belong to the group greater than a fourth volume of the speech voice of the third user which is output to the users who do not belong to the group.

19 . A non-transitory computer-readable medium storing thereon a communication assistance program that, when executed, causes a computer to:

detect a line of sight of a first user with respect to a screen in a real space, the screen showing a virtual space in which a plurality of user objects corresponding to a plurality of users are arranged, the virtual space being two-dimensional or three-dimensional;

detect a speech of the first user;

specify the second user as a conversation partner of the first user when the detected line of sight of the first user with respect to the screen in the real space overlaps with a user object corresponding to the second user in the virtual space and when the speech of the first user is detected;

set a group including the first user and the second user if the second user is specified as the conversation partner of the first user; and

output, to the first user, a speech voice of the second user if the second user is specified as the conversation partner of the first user and belongs to the group with a larger volume than a speech voice of the second user in a case if the second user is not specified as the conversation partner of the first user and does not belong to the group.

20 . The non-transitory computer-readable medium according to claim 19 , wherein the program, when executed, causes the computer to:

set a group region that visually indicates a range of the group in the virtual space;

when the first user speaks while gazing at the group region, make a first volume of a speech voice of the first user which is output to the users who belong to the group greater than a second volume of the speech voice of the first user which is output to the users who do not belong to the group; and

when a third user who does not belong to the group speaks while gazing at the group region, make a third volume of a speech voice of the third user which is output to the users who belong to the group greater than a fourth volume of the speech voice of the third user which is output to the users who do not belong to the group.