Systems and methods for identifying a media asset from an ambiguous audio indicator

1. A method for identifying a media asset, the method comprising:

capturing, from an environment where a user is present, an audio recording;

retrieving information about a user's location;

identifying a source of media available at the user's location;

determining content accessible from the source of media;

comparing the audio recording to the content to identify the media asset having a characteristic associated with the audio recording by:

determining a plurality of music tunes transmitted with the content;

comparing the frequency domain representation of the plurality of tones with each music tune of the plurality of music tunes to generate a respective similarity metric; and

in response to determining that the respective similarity metric is greater than a similarity threshold, identifying a respective music tune from the media asset corresponds to the audio recording provided by the user;

upon determining a match between the audio recording and the content, generating for display a recommendation of the media asset;

identifying, from the audio recording, a tune having audio characteristics that match with vocal characteristics of the user, wherein the tune includes a plurality of tones;

in response to identifying the tune, generating a frequency domain representation of the plurality of tones; and

transmitting a query based on the generated frequency domain representation to a music database.

2. The method of claim 1 , further comprising:

receiving a result indicating a failure to find a match in the music database based on the generated frequency domain representation.

3. The method of claim 1 , wherein identifying, from the audio recording, the tune having audio characteristics that match with vocal characteristics of the user, comprises:

extracting a set of mono signals from the audio recording;

for each mono signal from the set of mono signals:

generating a set of audio characteristics corresponding to the mono signal, wherein the set of audio characteristics includes any of mel-frequency cepstral coefficients (MFCC) and perceptual linear prediction relative spectra (PLP-RASTA);

retrieving, from a profile of the user, a set of vocal characteristics;

comparing each characteristic of the set of audio characteristics with a corresponding characteristic from the set of vocal characteristics that has a same type;

determining whether the set of audio characteristics and the set of vocal characteristics overlap for more than a similarity threshold; and

in response to determining that the set of audio characteristics and the set of vocal characteristics overlap for more than the similarity threshold, identifying the mono signal as a vocal signal from the user.

4. The method of claim 1 , wherein the determining the plurality of music tunes transmitted with the content of the first media asset comprises:

retrieving metadata associated with the content;

in response to determining that the metadata includes information relating to a theme song:

transmitting a query to the music database based on a title of the theme song; and

in response to the query, obtaining an audio asset of the theme song and generating a tune for the audio asset; and

in response to determining that the metadata includes no information relating to any theme song, performing audio analysis of the content to generate the plurality of music tunes.

5. A method for identifying a media asset, the method comprising:

capturing, from an environment where a user is present, an audio recording;

retrieving information about a user's location including retrieving, from a profile of the user, a location history of the user and an application usage history corresponding to the user;

identifying a source of media available at the user's location;

determining content accessible from the source of media;

comparing the audio recording to the content to identify the media asset having a characteristic associated with the audio recording;

upon determining a match between the audio recording and the content, generating for display a recommendation of the media asset;

searching the application usage history for one or more application usage records corresponding to when the user was present at the user's location; and

in response to identifying the one or more application usage records:

determining an application type, an application usage status and an application usage time duration for each of the one or more application usage records;

searching, an application usage table, for a distraction score corresponding to each application type;

computing a distraction metric based on the distraction score corresponding to each application type, the respective application usage status and the respective application usage time duration; and

in response to determining that the distraction metric is higher than a distraction threshold, determining that the user was not exposed to the retrieved content.

6. The method of claim 5 , wherein the retrieving, from the profile of the user, the location history of the user and the application usage history comprises:

transmitting a query to a device of the user for a GPS log and an application usage log;

in response to the query, obtaining the GPS log from the device of the user;

in response to receiving a notification that the GPS log is unavailable, transmitting, to a server, a query for a record of social media activities relating to the user;

in response to the query for the record of social media activities, searching the record of social media activities relating to the user for a first subset of social media activities, each social media activity from the subset identifying a location; and

storing the first subset of social media activities and corresponding locations as part of the location history.

7. The method of claim 6 , further comprising:

in response to receiving a notification that the application usage history is unavailable from the device of the user:

searching the record of social media activities relating to the user for a second subset of social media activities, each social media activity from the second subset indicates that the user is using a respective application; and

storing the second subset of social media activities and information relating to respective applications as part of the application usage history.

8. A system for identifying a media asset, the system comprising:

a storage device; and

control circuitry configured to:

capture, from an environment where a user is present, an audio recording;

retrieve information about a user's location;

identify a source of media available at the user's location;

determine content accessible from the source of media;

compare the audio recording to the content to identify the media asset having a characteristic associated with the audio recording by:

determining a plurality of music tunes transmitted with the content;

comparing the frequency domain representation of the plurality of tones with each music tune of the plurality of music tunes to generate a respective similarity metric; and

in response to determining that the respective similarity metric is greater than a similarity threshold, identifying a respective music tune from the media asset corresponds to the audio recording provided by the user;

upon determining a match between the audio recording and the content, generate for display a recommendation of the media asset;

identify, from the audio recording, a tune having audio characteristics that match with vocal characteristics of the user, wherein the tune includes a plurality of tones;

in response to identifying the tune, generate a frequency domain representation of the plurality of tones; and

transmit a query based on the generated frequency domain representation to a music database.

9. The system of claim 8 , wherein the control circuitry is further configured to:

receive a result indicating a failure to find a match in the music database based on the generated frequency domain representation.

10. The system of claim 8 , wherein the control circuitry, when identifying, from the audio recording, the tune having audio characteristics that match with vocal characteristics of the user, further configured to:

extract a set of mono signals from the audio recording;

for each mono signal from the set of mono signals:

generate a set of audio characteristics corresponding to the mono signal, wherein the set of audio characteristics includes any of mel-frequency cepstral coefficients (MFCC) and perceptual linear prediction relative spectra (PLP-RASTA);

retrieve, from a profile of the user, a set of vocal characteristics;

compare each characteristic of the set of audio characteristics with a corresponding characteristic from the set of vocal characteristics that has a same type;

determine whether the set of audio characteristics and the set of vocal characteristics overlap for more than a similarity threshold; and

in response to determining that the set of audio characteristics and the set of vocal characteristics overlap for more than the similarity threshold, identify the mono signal as a vocal signal from the user.

11. The system of claim 8 , wherein the control circuitry, when determining the plurality of music tunes transmitted with the content of the first media asset, further configured to:

retrieve metadata associated with the content;

in response to determining that the metadata includes information relating to a theme song:

transmit a query to the music database based on a title of the theme song; and

in response to the query, obtain an audio asset of the theme song and generating a tune for the audio asset; and

in response to determining that the metadata includes no information relating to any theme song, perform audio analysis of the content to generate the plurality of music tunes.

12. A system for identifying a media asset, the system comprising:

a storage device; and

control circuitry configured to:

capture, from an environment where a user is present, an audio recording;

retrieve information about a user's location including retrieving, from a profile of the user, a location history of the user and an application usage history corresponding to the user;

identify a source of media available at the user's location;

determine content accessible from the source of media;

compare the audio recording to the content to identify the media asset having a characteristic associated with the audio recording; and

upon determining a match between the audio recording and the content, generate for display a recommendation of the media asset;

search the application usage history for one or more application usage records corresponding to when the user was present at the user's location; and

in response to identifying the one or more application usage records:

determine an application type, an application usage status and an application usage time duration for each of the one or more application usage records;

search, an application usage table, for a distraction score corresponding to each application type;

compute a distraction metric based on the distraction score corresponding to each application type, the respective application usage status and the respective application usage time duration; and

in response to determining that the distraction metric is higher than a distraction threshold, determine that the user was not exposed to the retrieved content.

13. The system of claim 12 , wherein the retrieving, from the profile of the user, the location history of the user and the application usage history comprises:

transmit a query to a device of the user for a GPS log and an application usage log;

in response to the query, obtain the GPS log from the device of the user;

in response to receiving a notification that the GPS log is unavailable, transmit, to a server, a query for a record of social media activities relating to the user;

in response to the query for the record of social media activities, search the record of social media activities relating to the user for a first subset of social media activities, each social media activity from the subset identifying a location; and

store the first subset of social media activities and corresponding locations as part of the location history.

14. The system of claim 13 , wherein the control circuitry is further configured to:

in response to receive a notification that the application usage history is unavailable from the device of the user:

search the record of social media activities relating to the user for a second subset of social media activities, each social media activity from the second subset indicates that the user is using a respective application; and

store the second subset of social media activities and information relating to respective applications as part of the application usage history.