Multiple user recognition with voiceprints on online social networks
In one embodiment, a method includes, by one or more computing devices, receiving, from a client system at a first location, an audio input from an unknown user; identifying a first user of the online social network who is proximate to the first location; identifying the unknown user as a second user of the online social network based on a comparison of the audio input to one or more voiceprints of one or more candidate users stored by the online social network, respectively, wherein each voiceprint comprises audio data for auditory identification of a unique user of the online social network, and wherein each candidate user is within a threshold degree of separation of the first user within the online social network; and sending customized content to one or more of the first user or the second user based on their social-networking information.
1 . A method comprising:
receiving, by a computer system from a client system at a first location, an audio input from an unknown user;
identifying a first user of an online social network who is proximate to the first location;
identifying the unknown user as a second user of the online social network based on a comparison of the audio input to one or more voiceprints of one or more candidate users stored by the online social network, respectively, wherein each voiceprint comprises audio data for auditory identification of a unique user of the online social network, and wherein each candidate user is within a threshold degree of separation of the first user within the online social network; and
sending customized content to one or more of the first user or the second user based on their social-networking information;
wherein the client system is associated with the first user, and wherein identifying the unknown user is performed only if the first user has opted in to permitting identification of other users based on voiceprint analysis via audio from the first user's client system; and
wherein sending the customized content to the second user is performed only if the second user has opted in to permitting customization of content based on voiceprint analysis when identified by a device not authenticated to the second user.
2 . The method of claim 1 , further comprising performing an action associated with a voice command associated with the audio input.
3 . The method of claim 2 , the voice command comprising a word referring to the second user and a name of an object on a social network, the method further comprising:
identifying the object as being associated with a user identity of the second user.
4 . The method of claim 1 , wherein identifying the second user comprises accessing one or more voiceprints of one or more friends of the first user, wherein the one or more voiceprints stored by the online social network comprise the one or more voiceprints of the friends of the first user.
5 . The method of claim 4 , wherein the one or more friends of the first user are users of the online social network within a threshold degree of separation of the first user.
6 . The method of claim 1 , wherein the second user is associated with a voiceprint that matches the audio input.
7 . The method of claim 2 , further comprising determining to perform the action when permission settings indicate that the second user has permission to perform the action.
8 . The method of claim 7 , wherein the permission settings are associated with a user account of the second user.
9 . The method of claim 2 , further comprising determining to perform the action when a determined relationship status between the first user and the identified second user indicates that the identified second user is within a threshold degree of separation of the first user on an online social network.
10 . The method of claim 1 , further comprising:
identifying the second user as a new user when the audio input does not correspond to the one or more voiceprints; and
generating a new voiceprint for the new user based on the audio input; and storing the new voiceprint for subsequent access by the online social network.
11 . The method of claim 1 , further comprising identifying one or more voice commands using voice recognition on the audio input.
12 . The method of claim 11 , wherein at least one of the one or more voice commands comprises a name of an action associated with the command.
13 . The method of claim 11 , wherein at least one of the one or more voice commands comprises a user name that refers to a plurality of users having the same name, the method further comprising:
determining which of the plurality of users the name refers to based on the second user's social graph connections.
14 . The method of claim 13 , wherein the determining comprises:
comparing a degree of separation between the second user and a first one of the plurality of users to a degree of separation between the second user and the second one of the plurality of users; and
selecting the user having the smaller degree of separation as the user the name refers to.
15 . The method of claim 13 , wherein the determining comprises:
comparing an affinity coefficient calculated based on the second user and the first one of the plurality of users to an affinity coefficient calculated based on the second user and the second one of the plurality of users; and
selecting the user having the greater affinity as the user the name refers to.
16 . The method of claim 1 , wherein the customized content comprises advertisements, news feeds, push notifications, place tips, coupons, or suggestions.
17 . The method of claim 1 , wherein the second user has checked-in at the same location as the first user.
18 . The method of claim 1 , wherein the customized content comprises content associated with the first location.
19 . The method of claim 1 , wherein sending the customized content to one or more of the first user or the second user is performed only if the one or more of the first user or the second user has opted in to permitting customization of content for the respective first user or second user based on voiceprint analysis.
20 . One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
receive, from a client system at a first location, an audio input from an unknown user;
identify a first user of an online social network who is proximate to the first location;
identify the unknown user as a second user of the online social network based on a comparison of the audio input to one or more voiceprints of one or more candidate users stored by the online social network, respectively, wherein each voiceprint comprises audio data for auditory identification of a unique user of the online social network, and wherein each candidate user is within a threshold degree of separation of the first user within the online social network; and
send customized content to one or more of the first user or the second user based on their social-networking information;
wherein the client system is associated with the first user, and wherein to identify the unknown user is to be performed only if the first user has opted in to permit identification of other users based on voiceprint analysis via audio from the first user's client system; and
wherein sending the customized content to the second user is performed only if the second user has opted in to permitting customization of content based on voiceprint analysis when identified by a device not authenticated to the second user.
21 . The one or more computer-readable non-transitory storage media of claim 20 , wherein to send the customized content to one or more of the first user or the second user is to be performed only if the one or more of the first user or the second user has opted in to permit customization of content for the respective first user or second user based on voiceprint analysis.
22 . A system comprising:
one or more processors; and
a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to:
receive, from a client system at a first location, an audio input from an unknown user;
identify a first user of an online social network who is proximate to the first location;
identify the unknown user as a second user of the online social network based on a comparison of the audio input to one or more voiceprints of one or more candidate users stored by the online social network, respectively, wherein each voiceprint comprises audio data for auditory identification of a unique user of the online social network, and wherein each candidate user is within a threshold degree of separation of the first user within the online social network; and
send customized content to one or more of the first user or the second user based on their social-networking information;
wherein the client system is associated with the first user, and wherein to identify the unknown user is to be performed only if the first user has opted in to permit identification of other users based on voiceprint analysis via audio from the first user's client system; and
wherein sending the customized content to the second user is performed only if the second user has opted in to permitting customization of content based on voiceprint analysis when identified by a device not authenticated to the second user.
23 . The system of claim 22 , wherein to send the customized content to one or more of the first user or the second user is to be performed only if the one or more of the first user or the second user has opted in to permit customization of content for the respective first user or second user based on voiceprint analysis.