CLAIMS We claim:
1. A system (600) for automatically identifying and ranking key moments in a
media asset, the system (600) comprising:
at least one processor (502);
a non-transitory, computer-readable storage medium (506) operably and communicatively coupled to the at least one processor (502) and configured to store the media asset and computer program instructions executable by the at least one processor (502); and
a key moments engine (507) configured to define the computer program instructions, which when executed by the at least one processor (502), cause the at least one processor (502) to:
extract an audio stream from the media asset and store the audio stream as an audio file;
divide the audio file into sub-second audio segments; compute an audio signal level for each of the sub-second audio segments and generate an array of audio signal levels for the audio file;
generate clusters of the audio signal levels from the array of audio signal levels;
dynamically determine threshold levels for classifying the audio signal levels in the array using the clusters;
identify the key moments from the classified audio signal levels; and compute a rank for each of the identified key moments based on ranking criteria.
2. The system (600) as claimed in claim 1, wherein the audio signal level is
measured in decibels relative to full scale.

3. The system (600) as claimed in claim 1, wherein one or more of the computer program instructions, which when executed by the at least one processor (502), cause the at least one processor (502) to store the audio signal level as an absolute value of the audio signal level for the generation of the clusters free of errors.
4. The system (600) as claimed in claim 1, wherein the key moments engine (507) is configured to execute at least one of a plurality of clustering algorithms for generating the clusters of the audio signal levels, wherein the at least one of the clustering algorithms is a k-means clustering algorithm.
5. The system (600) as claimed in claim 1, wherein the audio signal levels are classified as one of high audio signal levels, medium audio signal levels, and low audio signal levels.
6. The system (600) as claimed in claim 1, wherein, for the identification of the key moments from the classified audio signal levels, one or more of the computer program instructions, which when executed by the at least one processor (502), cause the at least one processor (502) to:
analyze the classified audio signal levels comprising an array of events, wherein one of a medium one of the classified audio signal levels and a high one of the classified audio signal levels is identified as a starting point of each of the events, and wherein an end point of the each of the events is identified on detecting a low one of the classified audio signal levels in the array;
process the events for identifying the key moments by performing one or more of:
discarding events containing only medium audio signal levels and low
audio signal levels, from the array of events;
discarding events that overlap boundaries of accompanying elements
of the media asset, from the array of events, wherein the accompanying

elements of the media asset comprise songs, start credits, and end credits of the media asset;
merging one or more of the events that are closer to each other in relation to a predetermined duration; and
discarding events that are short in duration from the array of events.
7. The system (600) as claimed in claim 1, wherein one or more of the computer program instructions, which when executed by the at least one processor (502), cause the at least one processor (502) to process events with non-distinguishable audio signal levels for the identification of the key moments.
8. The system (600) as claimed in claim 1, wherein one or more of the computer program instructions, which when executed by the at least one processor (502), cause the at least one processor (502) to represent the each of the identified key moments using a start time code and an end time code.
9. The system (600) as claimed in claim 8, wherein one or more of the computer program instructions, which when executed by the at least one processor (502), cause the at least one processor (502) to adjust the start time code and the end time code of the each of the identified key moments to boundaries of shots of the media asset to enhance a visual representation of the identified key moments.
10. The system (600) as claimed in claim 8, wherein one or more of the computer program instructions, which when executed by the at least one processor (502), cause the at least one processor (502) to discard fringe shots that end just before the start time code of the each of the identified key moments and fringe shots that start just after the end time code of the each of the identified key moments.

11. The system (600) as claimed in claim 1, wherein one or more of the computer program instructions, which when executed by the at least one processor (502), cause the at least one processor (502) to create a dictionary for the each of the identified key moments for storing the audio signal levels of audio segments in the each of the identified key moments, and a start time code and an end time code of an event defining the each of the identified key moments, wherein the dictionary comprises shots that fall inside the each of the identified key moments.
12. The system (600) as claimed in claim 1, wherein the ranking criteria comprise one or more of variations in the audio signal levels of the identified key moments, presence of one or more key actors in the media asset determined using a reference database of key actors, presence of scenes of interest in the media asset, and an average audio signal level of the each of the identified key moments.
13. The system (600) as claimed in claim 1, wherein one or more of the computer program instructions, which when executed by the at least one processor (502), cause the at least one processor (502) to generate a report comprising an audio plot of the each of the identified key moments and the shots in the each of the identified key moments, the computed rank of the each of the identified key moments, and a start time code and an end time code of the each of the identified key moments.
14. A method executed by a key moments engine (507) operably coupled to at least one processor (502) for automatically identifying and ranking key moments in a media asset, the method comprising:
extracting (101) an audio stream from the media asset and storing the audio stream as an audio file;
dividing (102) the audio file into sub-second audio segments;

computing (103) an audio signal level for each of the sub-second audio segments and generating an array of audio signal levels for the audio file;
generating (104) clusters of the audio signal levels from the array of audio signal levels;
dynamically determining (105) threshold levels for classifying the audio signal levels in the array using the clusters;
identifying (106) the key moments from the classified audio signal levels; and
computing (107) a rank for each of the identified key moments based on ranking criteria.
15. The method as claimed in claim 14, wherein the audio signal level is measured in decibels relative to full scale.
16. The method as claimed in claim 14, comprising storing the audio signal level as an absolute value of the audio signal level by the key moments engine (507) for the generation of the clusters free of errors.
17. The method as claimed in claim 14, wherein the key moments engine (507) is configured to execute at least one of a plurality of clustering algorithms for generating the clusters of the audio signal levels, wherein the at least one of the clustering algorithms is a k-means clustering algorithm.
18. The method as claimed in claim 14, wherein the audio signal levels are classified as one of high audio signal levels, medium audio signal levels, and low audio signal levels.
19. The method as claimed in claim 14, wherein the identification of the key moments from the classified audio signal levels comprises:
analyzing the classified audio signal levels comprising an array of events by the key moments engine (507), wherein one of a medium one of the

classified audio signal levels and a high one of the classified audio signal levels is identified as a starting point of each of the events, and wherein an end point of the each of the events is identified on detecting a low one of the classified audio signal levels in the array;
processing the events for identifying the key moments by performing one or more of:
discarding events containing only medium audio signal levels and low audio signal levels, from the array of events, by the key moments engine (507);
discarding events that overlap boundaries of accompanying elements of the media asset, from the array of events, by the key moments engine (507), wherein the accompanying elements of the media asset comprise songs, start credits, and end credits of the media asset;
merging one or more of the events that are closer to each other in relation to a predetermined duration by the key moments engine (507); and discarding events that are short in duration from the array of events by the key moments engine (507).
20. The method as claimed in claim 14, comprising processing events with non-distinguishable audio signal levels by the key moments engine (507) for the identification of the key moments.
21. The method as claimed in claim 14, comprising representing the each of the identified key moments using a start time code and an end time code by the key moments engine (507).
22. The method as claimed in claim 21, comprising adjusting the start time code and the end time code of the each of the identified key moments to boundaries of shots of the media asset by the key moments engine (507) to enhance a visual representation of the identified key moments.

23. The method as claimed in claim 21, comprising discarding, by the key moments engine (507), fringe shots that end just before the start time code of the each of the identified key moments and fringe shots that start just after the end time code of the each of the identified key moments.
24. The method as claimed in claim 14, comprising creating a dictionary for the each of the identified key moments by the key moments engine (507) for storing the audio signal levels of audio segments in the each of the identified key moments, and a start time code and an end time code of an event defining the each of the identified key moments, wherein the dictionary comprises shots that fall inside the each of the identified key moments.
25. The method as claimed in claim 14, wherein the ranking criteria comprise one or more of variations in the audio signal levels of the identified key moments, presence of one or more key actors in the media asset determined using a reference database of key actors, presence of scenes of interest in the media asset, and an average audio signal level of the each of the identified key moments.
26. The method as claimed in claim 14, comprising generating, by the key moments engine (507), a report comprising an audio plot of the each of the identified key moments and the shots in the each of the identified key moments, the computed rank of the each of the identified key moments, and a start time code and an end time code of the each of the identified key moments. Jl