Methods and systems for automatically evaluating an audio description track of a media asset

1. A method for automatically evaluating an audio description track of a media asset, the method comprising:

generating for display, on a display screen, a listing for a media asset, wherein the media asset comprises a plurality of sequentially ordered video frames and an audio track corresponding to the plurality of video frames;

receiving, from a user, a request to evaluate an audio description track of the media asset, wherein the audio description track comprises audio content that supplements the audio track with audio descriptions of visual events occurring in the media asset;

initializing a rating of the audio description track to a default value, wherein the rating of the audio description track indicates a numerical evaluation of how comprehensively the audio description track describes the visual events occurring in the media asset;

receiving a first video frame and a second video frame of the plurality of sequentially ordered video frames, wherein:

the first video frame is ordered before the second video frame in the plurality of sequentially ordered video frames;

the first video frame corresponds to a first time; and

the second video frame corresponds to a second time;

detecting an object in the first video frame;

detecting the object in the second video frame;

determining a difference in a characteristic of the object between the first video frame and the second video frame;

comparing the difference to a threshold difference;

based on the difference exceeding the threshold difference, determining an audio characteristic in a portion of the audio description track that corresponds to a range of time that includes the first time and the second time;

comparing the audio characteristic to a threshold audio characteristic;

based on the audio characteristic exceeding the threshold audio characteristic, increasing the rating of the audio description track by a unit; and

generating for display an indication of the rating.

2. The method of claim 1 , wherein detecting the object in the first video frame comprises:

detecting a first object and a second object in the first video frame;

determining a first subset of a plurality of pixels of a display screen in which the first object occurs in the first video frame;

determining a second subset of the plurality of pixels in which the second object occurs in the first video frame;

determining that a number of pixels in the first subset is greater than a number of pixels in the second subset; and

selecting the first object to be the object.

3. The method of claim 1 , wherein detecting the object in the first video frame comprises:

detecting a first object and a second object in the first video frame;

receiving metadata associated with the first video frame;

detecting an identifier of the first object in the metadata; and

selecting the first object to be the object.

4. The method of claim 3 , wherein the first object is a character, and detecting the identifier of the first object in the metadata comprises detecting at least one of a name of the character and an actor who plays the character.

5. The method of claim 1 , wherein the characteristic of the object is a position of the object.

6. The method of claim 5 , wherein:

determining the difference in the characteristic of the object between the first video frame and the second video frame comprises:

assigning an address to each pixel of a plurality of pixels of the display screen, wherein each address comprises a horizontal address corresponding to a horizontal position on the display screen of each pixel and a vertical address corresponding to a vertical position on the display screen of each pixel;

determining a first subset of the plurality of pixels in which the object occurs in the first video frame;

determining a second subset of the plurality of pixels in which the object occurs in the second video frame;

calculating a first horizontal mean, wherein the first horizontal mean corresponds to a mean of horizontal addresses of the first subset;

calculating a first vertical mean, wherein the first vertical mean corresponds to a mean of vertical addresses of the first subset;

calculating a second horizontal mean, wherein the second horizontal mean corresponds to a mean of horizontal addresses of the second subset;

calculating a second vertical mean, wherein the second vertical mean corresponds to a mean of vertical addresses of the second subset;

subtracting the second horizontal mean from the first horizontal mean to obtain a horizontal difference;

subtracting the second vertical mean from the first vertical mean to obtain a vertical difference; and

comparing the difference to the threshold difference comprises:

comparing an absolute value of the horizontal difference to a threshold number of pixels;

comparing an absolute value of the vertical difference to the threshold number of pixels; and

determining the difference to exceed the threshold difference if the absolute value of the horizontal difference or the absolute value of the vertical difference exceeds the threshold number of pixel.

7. The method of claim 1 , further comprising based on the audio characteristic not exceeding the threshold audio characteristic, generating audio content corresponding to at least one of the object and the characteristic of the object in the portion of the audio description track.

8. The method of claim 1 , wherein determining the audio characteristic in the portion of the audio description track comprises determining a volume of audio content in the portion of the audio description track.

9. The method of claim 1 , wherein determining the audio characteristic in the portion of the audio description track comprises:

identifying the object with an identifier;

accessing a database of synonyms;

retrieving from the database a plurality of keywords for the identifier, wherein the keywords are synonyms for the identifier; and

determining a number of times in which a keyword of the plurality of keywords or the identifier occurs in the portion of the audio description track.

10. The method of claim 1 , wherein generating for display the indication of the rating comprises generating for display at least one of a word, icon, size of the listing, color of the listing, and presence of the listing corresponding to the rating.

11. A system for automatically evaluating an audio description track of a media asset, the method comprising:

control circuitry configured to:

generate for display, on a display screen, a listing for a media asset, wherein the media asset comprises a plurality of sequentially ordered video frames and an audio track corresponding to the plurality of video frames;

receive, from a user, a request to evaluate an audio description track of the media asset, wherein the audio description track comprises audio content that supplements the audio track with audio descriptions of visual events occurring in the media asset;

initialize a rating of the audio description track to a default value, wherein the rating of the audio description track indicates a numerical evaluation of how comprehensively the audio description track describes the visual events occurring in the media asset;

receive a first video frame and a second video frame of the plurality of sequentially ordered video frames, wherein:

the first video frame is ordered before the second video frame in the plurality of sequentially ordered video frames;

the first video frame corresponds to a first time; and

the second video frame corresponds to a second time;

detect an object in the first video frame;

detect the object in the second video frame;

determine a difference in a characteristic of the object between the first video frame and the second video frame;

compare the difference to a threshold difference;

based on the difference exceeding the threshold difference, determine an audio characteristic in a portion of the audio description track that corresponds to a range of time that includes the first time and the second time;

compare the audio characteristic to a threshold audio characteristic;

based on the audio characteristic exceeding the threshold audio characteristic, increase the rating of the audio description track by a unit; and

generate for display an indication of the rating.

12. The system of claim 11 , wherein the control circuitry is further configured, when detecting the object in the first video frame, to:

detect a first object and a second object in the first video frame;

determine a first subset of a plurality of pixels of a display screen in which the first object occurs in the first video frame;

determine a second subset of the plurality of pixels in which the second object occurs in the first video frame;

determine that a number of pixels in the first subset is greater than a number of pixels in the second subset; and

select the first object to be the object.

13. The system of claim 11 , wherein the control circuitry is further configured, when detecting the object in the first video frame, to:

detect a first object and a second object in the first video frame;

receive metadata associated with the first video frame;

detect an identifier of the first object in the metadata; and

select the first object to be the object.

14. The system of claim 13 , wherein the first object is a character, and wherein the control circuitry is further configured, when detecting the identifier of the first object in the metadata, to detect at least one of a name of the character and an actor who plays the character.

15. The system of claim 11 , wherein the characteristic of the object is a position of the object.

16. The system of claim 15 , wherein:

the control circuitry is further configured, when determining the difference in the characteristic of the object between the first video frame and the second video frame, to:

assign an address to each pixel of a plurality of pixels of the display screen, wherein each address comprises a horizontal address corresponding to a horizontal position on the display screen of each pixel and a vertical address corresponding to a vertical position on the display screen of each pixel;

determine a first subset of the plurality of pixels in which the object occurs in the first video frame;

determine a second subset of the plurality of pixels in which the object occurs in the second video frame;

calculate a first horizontal mean, wherein the first horizontal mean corresponds to a mean of horizontal addresses of the first subset;

calculate a first vertical mean, wherein the first vertical mean corresponds to a mean of vertical addresses of the first subset;

calculate a second horizontal mean, wherein the second horizontal mean corresponds to a mean of horizontal addresses of the second subset;

calculate a second vertical mean, wherein the second vertical mean corresponds to a mean of vertical addresses of the second subset;

subtract the second horizontal mean from the first horizontal mean to obtain a horizontal difference; and

subtract the second vertical mean from the first vertical mean to obtain a vertical difference; and

the control circuitry is further configured, when comparing the difference to the threshold difference, to:

compare an absolute value of the horizontal difference to a threshold number of pixels;

compare an absolute value of the vertical difference to the threshold number of pixels; and

determine the difference to exceed the threshold difference if the absolute value of the horizontal difference or the absolute value of the vertical difference exceeds the threshold number of pixels.

17. The system of claim 11 , wherein the control circuitry is further configured, based on the audio characteristic not exceeding the threshold audio characteristic, to generate audio content corresponding to at least one of the object and the characteristic of the object in the portion of the audio description track.

18. The system of claim 11 , wherein the control circuitry is further configured, when determining the audio characteristic in the portion of the audio description track, to determine a volume of audio content in the portion of the audio description track.

19. The system of claim 11 , wherein the control circuitry is further configured, when determining the audio characteristic in the portion of the audio description track, to:

identify the object with an identifier;

access a database of synonyms;

retrieve from the database a plurality of keywords for the identifier, wherein the keywords are synonyms for the identifier; and

determine a number of times in which a keyword of the plurality of keywords or the identifier occurs in the portion of the audio description track.

20. The system of claim 11 , wherein the control circuitry is further configured, when generating for display the indication of the rating, to generate for display at least one of a word, icon, size of the listing, color of the listing, and presence of the listing corresponding to the rating.