SYSTEMS AND METHODS FOR RECOGNIZING USER INFORMATION
A conferencing system is configured, for an interval of time, to receive time-dependent input data from a first user, the time-dependent input data obtained via a capturing device. The conferencing system is configured to receive profile data for the first user, analyze the time-dependent input data and the profile data for the first user using a computer-based model to obtain at least one classifier score for a classifier of a reaction of the first user, and transmit the at least one classifier score for the classifier to a second user.
1 - 20 . (canceled)
21 . A conferencing system configured, for an interval of time, to:
receive time-dependent input data from users;
receive profile data for the users;
determine classifier scores for reaction classifiers based on the time-dependent input data and the profile data for each user using a computer-based model, wherein each of the reaction classifiers represents a type of state of the user, and the classifier score represents a score for the type of state of the user;
determine a correlation between the classifier scores for the reaction classifiers of the users; and
present the correlation.
22 . The system of claim 21 , wherein the classifier scores for the reaction classifiers are determined using the computer-based model comprising a neural network.
23 . The system of claim 21 , wherein the time-dependent input data comprises a sequence of images of faces of the users, and wherein determining the classifier scores for the reaction classifiers comprises:
applying the computer-based model for identifying the types of state of the users from the sequence of the images;
assigning the reaction classifiers to the identified types of state;
applying a computer-based model for identifying amplitudes of the types of state; and
assigning the classifier scores for the identified amplitudes.
24 . The system of claim 21 , wherein the time-dependent input data comprises one of an audio input, a video input, or an action input.
25 . The system of claim 21 , wherein the time-dependent input data comprises an audio data of a speech, including a sequence of phonemes of the users; and
wherein determining the classifier scores for the reaction classifiers comprises:
applying the computer-based model for identifying the types of state of the users from the sequence of the phonemes;
assigning the reaction classifiers to the identified the types of state;
applying the computer-based model for identifying amplitudes of the types of state; and
assigning the classifier scores for the identified amplitudes.
26 . The system of claim 25 , wherein the audio data comprises information about at least one of a pitch, a volume, or a tempo of the speech.
27 . The system of claim 21 , further configured to transmit the classifier scores for the reaction classifiers to other users.
28 . The system of claim 21 , configured to transmit the correlation to other users of the conference.
29 . A computer-implemented method comprising:
receiving time-dependent input data from users, the time-dependent input data;
receiving profile data for the users;
determining classifier scores for reaction classifiers based on analyzing the time-dependent input data and the profile data for each user using a computer-based model, wherein each of the reaction classifiers represents a type of state of the user, and the classifier score represents a score for the type of state of the user;
determining a correlation between the classifier scores for the reaction classifiers of the users; and
presenting the correlation.
30 . The method of claim 29 , wherein the classifier scores for the reaction classifiers are determined using the computer-based model comprising a neural network.
31 . The method of claim 29 , wherein the time-dependent input data comprises a sequence of images of faces of the users, and wherein determining the classifier scores for the reaction classifiers comprises:
applying the computer-based model for identifying the types of state of the users from the sequence of the images;
assigning the reaction classifiers to the identified types of state;
applying a computer-based model for identifying an amplitudes of the types of state; and
assigning the classifier scores for the identified amplitudes.
32 . The method of claim 29 , wherein the time-dependent input data comprises one of an audio input, a video input, or an action input.
33 . The method of claim 29 , wherein the time-dependent input data comprises an audio data of a speech, including a sequence of phonemes of the users; and
wherein determining the classifier scores for the reaction classifiers comprises:
applying the computer-based model for identifying the types of state of the users from the sequence of the phonemes;
assigning the reaction classifiers to the identified types of state;
applying the computer-based model for identifying amplitudes of the types of state; and
assigning the classifier scores for the identified amplitudes.
34 . The system of claim 33 , wherein the audio data comprises information about at least one of a pitch, a volume, or a tempo of the speech.
35 . The method of claim 29 , further configured to transmit the classifier scores for the reaction classifiers to other users.
36 . The method of claim 29 , configured to transmit the correlation to other users of the conference.
37 . A non-transitory, computer-readable medium storing instructions that, when executed by a processor, cause:
receiving time-dependent input data from users, the time-dependent input data;
receiving profile data for the users;
determining classifier scores for reaction classifiers based on analyzing the time-dependent input data and the profile data for each user using a computer-based model, wherein each of the reaction classifiers represents a type of state of the user, and the classifier score represents a score for the type of state of the user;
determining a correlation between the classifier scores for the reaction classifiers of the users; and
presenting the correlation.
38 . The method of claim 37 , wherein the classifier scores for the reaction classifiers are determined using the computer-based model comprising a neural network.
39 . The method of claim 37 , wherein the time-dependent input data comprises a sequence of images of faces of the users, and wherein determining the classifier scores for the reaction classifiers comprises:
applying the computer-based model for identifying the types of state of the users from the sequence of the images;
assigning the reaction classifiers to the identified types of state;
applying a computer-based model for identifying an amplitudes of the types of state; and
assigning the classifier scores for the identified amplitudes.
40 . The method of claim 37 , wherein the time-dependent input data comprises an audio data of a speech, including a sequence of phonemes of the users; and
wherein determining the classifier scores for the reaction classifiers comprises:
applying the computer-based model for identifying the types of state of the users from the sequence of the phonemes;
assigning the reaction classifiers to the identified types of state;
applying the computer-based model for identifying amplitudes of the types of state; and
assigning the classifier scores for the identified amplitudes.