Systems and methods for determining meaning of cultural gestures based on voice detection

Abstract

In some embodiments, control circuitry may detect a voice communication from a human using voice detection circuitry during playback of a media asset being consumed by the user. Control circuitry may then identify an accent characteristic of the voice communication. Control circuitry may cross-reference the accent characteristic against listings of an accent database and then determine, based on the cross-referencing of the accent characteristic a country of origin of the human. Control circuitry may detect, using imaging circuitry, a gesture made by the human. Control circuitry may then cross-reference the gesture against listings of a gesture database associated with the country of origin and then determine based on the cross-referencing of the gesture, a meaning of the gesture in relation to the media asset.

1 - 50 . (canceled) 
     
     
         51 . A method for providing media recommendations based on a person's culture as determined by their accent and a gesture, the method comprising:
 generating for display a media asset for playback;   detecting, by voice detection circuitry, a voice communication from a user, during playback of the media asset;   identifying an accent characteristic of the voice communication;   determining, from entries of an accent database, a culture corresponding to the accent characteristic;   detecting, by imaging circuitry, a gesture made by the user in relation to the media asset;   determining, from entries of a gesture database associated with the culture, a meaning of the gesture; and   generating, for the user, a media recommendation based on the meaning of the gesture in relation to the media asset.   
     
     
         52 . The method of  claim 51 , wherein the identifying of the accent characteristic comprises:
 detecting, by voice processing circuitry, a respective manner of annunciating each syllable of a plurality of syllables of the voice communication;   determining whether a threshold amount of syllables correspond to a single respective manner; and   in response to determining that the threshold amount of syllables corresponds to the single respective manner, identifying the accent characteristics by determining that the single respective manner corresponds to the accent characteristic.   
     
     
         53 . The method of  claim 52 , wherein detecting the respective manner of annunciating each syllable comprises comparing the respective manner of annunciating each syllable to a known universe of potential manners of annunciating each syllable, and identifying a match between the respective manner and a manner in the known universe of potential manners. 
     
     
         54 . The method of  claim 51 , wherein the meaning comprises at least one of: an indication of enjoyment of the media asset by the user; an indication of distaste for the media asset by the user; an indication that the user wishes to suspend viewing the media asset; and an indication that the user wishes to alert information about the media asset to another user. 
     
     
         55 . The method of  claim 51 , wherein the media recommendation is tailored to a country associated with the culture. 
     
     
         56 . The method of  claim 55 , wherein multiple countries associated with the culture are determined based on the comparing of the accent characteristic, and wherein a single country of the multiple countries is identified by:
 determining, by imaging circuitry, body characteristics of the user;   comparing the body characteristics of the user to listings of a body characteristic database that correspond to each country of the multiple countries; and   determining, based on the comparing of the body characteristics of the user to the listings of the body characteristic database, the country associated with the culture.   
     
     
         57 . The method of  claim 51 , wherein the meaning of the gesture varies based on the culture. 
     
     
         58 . The method of  claim 51 , wherein detecting the voice communication comprises:
 detecting, by a microphone, audio comprising communication from the user and ambient noise comprising audio of the media asset; and   isolating the audio comprising communication from the user from the ambient noise to detect the voice communication.   
     
     
         59 . The method of  claim 51 , wherein the gesture comprises at least one of a hand movement, a leg movement, a body movement, and a collision between a body part of the user and an inanimate object. 
     
     
         60 . The method of  claim 51 , wherein the media recommendation is of an additional media asset or a product. 
     
     
         61 . A system for providing recommendations in relation to media assets in gesture recognition computer systems by determining a meaning of cultural gestures based on voice detection, the system comprising:
 voice detection circuitry;   imaging circuitry configured to generate for display a media asset for playback; and   control circuitry configured to:   detect, by voice detection circuitry, a voice communication from a user, during playback of the media asset;   identify an accent characteristic of the voice communication;   determine, from entries of an accent database, a culture corresponding to the accent characteristic;   detect, by imaging circuitry, a gesture made by the user in relation to the media asset;   determine, from entries of a gesture database associated with the culture, a meaning of the gesture; and   generate, for the user, a media recommendation based on the meaning of the gesture in relation to the media asset.   
     
     
         62 . The system of  claim 61 , wherein the control circuitry, when identifying of the accent characteristic, is further configured to:
 detect, using voice processing circuitry, a respective manner of annunciating each syllable of a plurality of syllables of the voice communication;   determine whether a threshold amount of syllables correspond to a single respective manner; and   in response to determining that the threshold amount of syllables corresponds to the single respective manner, identify the accent characteristics by determining that the single respective manner corresponds to the accent characteristic.   
     
     
         63 . The system of  claim 62 , wherein the control circuitry, when detecting the respective manner of annunciating each syllable, is further configured to:
 compare the respective manner of annunciating each syllable to a known universe of potential manners of annunciating each syllable; and   identify a match between the respective manner and a manner in the known universe of potential manners.   
     
     
         64 . The system of  claim 61 , wherein the meaning comprises at least one of: an indication of enjoyment of the media asset by the user; an indication of distaste for the media asset by the user; an indication that the user wishes to suspend viewing the media asset; and an indication that the user wishes to alert information about the media asset to another user. 
     
     
         65 . The system of  claim 61 , wherein the recommendation is tailored to a country associated with the culture. 
     
     
         66 . The system of  claim 65 , wherein multiple countries associated with the culture are determined based on the comparing of the accent characteristic, and wherein the control circuitry is further configured to identify a single country of the multiple countries by:
 determining, by imaging circuitry, body characteristics of the user;   comparing the body characteristics of the user to listings of a body characteristic database that correspond to each country of the multiple countries; and   determining, based on the comparing of the body characteristics of the user to the listings of the body characteristic database, the country associated with the culture.   
     
     
         67 . The system of  claim 61 , wherein the meaning of the gesture varies based on the culture. 
     
     
         68 . The system of  claim 61 , wherein the control circuitry, when detecting the voice communication, is further configured to:
 detect, using a microphone, audio comprising communication from the user and ambient noise comprising audio of the media asset; and   isolate the audio comprising communication from the user from the ambient noise to detect the voice communication.   
     
     
         69 . The system of  claim 61 , wherein the gesture comprises at least one of a hand movement, a leg movement, a body movement, and a collision between a body part of the user and an inanimate object. 
     
     
         70 . The system of  claim 61 , wherein the recommendation is of an additional media asset or a product.