Systems and methods for associating context to subtitles during live events
Systems and methods are provided herein for providing context to users who access video conferences late. This may be accomplished by a system receiving an audio segment of a video conference and generating a subtitle corresponding to the audio segment. The system may determine a summary relating to the audio segment and then display the subtitle, summary, and video conference on a device. The system allows a user, who accesses a video conference late, to quickly and accurately understand the current video conference discussion, improving the user's experience and increasing the productivity of the video conference.
1. A computer-implemented method for generating contextual information, the method comprising:
generating a plurality of subtitles corresponding to a video conference;
generating a first summary associated with a first subject using a first subset of the plurality of subtitles;
generating a second summary associated with a second subject using a second subset of the plurality of subtitles;
storing the first summary and the second summary in a database comprising a plurality of entries, wherein the plurality of entries associates one or more summaries with one or more subjects;
receiving a first audio segment of the video conference;
generating a first subtitle comprising a plurality of words using the first audio segment, wherein the first subtitle corresponds to the first audio segment;
selecting a word of the plurality of words;
accessing the database comprising the plurality of entries;
determining that a first entry of the plurality of entries associates the selected word with the first subject; and
displaying the first subtitle, the first summary, the second summary, and the video conference on a screen of a first device at the same time, wherein:
the first subtitle and the first summary are displayed in a first format;
the second summary is displayed in a second format; and
the first format is different than the second format.
2. The method of claim 1 , further comprising:
receiving a second audio segment of the video conference;
generating a second subtitle comprising a second plurality of words using the second audio segment, wherein the second subtitle corresponds to the second audio segment;
selecting a word of the second plurality of words;
accessing the database;
determining that a second entry of the plurality of entries associates the selected word of the second plurality of words with the second subject; and
displaying the second subtitle, the second summary, the first summary, and the video conference on the screen of the first device at the same time.
3. The method of claim 1 , wherein the first summary is generated using a natural language process algorithm.
4. The method of claim 1 , wherein the video conference is a live video conference.
5. The method of claim 1 , wherein the video conference is a recorded video conference.
6. The method of claim 1 , wherein the first format corresponds to a first color and the second format corresponds to a second color.
7. The method of claim 1 , wherein the first format corresponds to a first indicator and the second format corresponds to a second indicator.
8. The method of claim 1 , wherein the first format corresponds to a first font and the second format corresponds to a second font.
9. The method of claim 1 , wherein the first format corresponds to a first size and the second format corresponds to a second size.
10. An apparatus comprising:
control circuitry; and
at least one memory including computer program code for one or more programs, the at least one memory and the computer program code configured to, with the control circuitry, cause the apparatus to perform at least the following:
generate a plurality of subtitles corresponding to a video conference;
generate a first summary associated with a first subject using a first subset of the plurality of subtitles;
generate a second summary associated with a second subject using a second subset of the plurality of subtitles;
store the first summary and the second summary in a database comprising a plurality of entries, wherein the plurality of entries associates one or more words summaries with one or more subjects;
receive a first audio segment of the video conference;
generate a first subtitle comprising a plurality of words using the first audio segment, wherein the first subtitle corresponds to the first audio segment;
select a word of the plurality of words;
access the database comprising the plurality of entries;
determine that a first entry of the plurality of entries associates the selected word with the first subject; and
generate the first subtitle, the first summary, the second summary, and the video conference for display at the same time on a screen of a first device, wherein:
the first subtitle and the first summary are displayed in a first format;
the second summary is displayed in a second format; and
the first format is different than the second format.
11. The apparatus of claim 10 , wherein the apparatus is further caused to:
receive a second audio segment of the video conference;
generate a second subtitle comprising a second plurality of words using the second audio segment, wherein the second subtitle corresponds to the second audio segment;
select a word of the second plurality of words;
access the database;
determine that a second entry of the plurality of entries associates the selected word of the second plurality of words with the second subject; and
generate the second subtitle, the second summary, the first summary, and the video conference for display at the same time on the screen of the first device.
12. The apparatus of claim 10 , wherein the apparatus is further caused to generate the first summary using a natural language process algorithm.
13. The apparatus of claim 10 , wherein the video conference is a live video conference.
14. The apparatus of claim 10 , wherein the video conference is a recorded video conference.
15. A non-transitory computer-readable medium having instructions encoded thereon that, when executed by control circuitry, cause the control circuitry to:
generate a plurality of subtitles corresponding to a video conference;
generate a first summary associated with a first subject using a first subset of the plurality of subtitles;
generate a second summary associated with a second subject using a second subset of the plurality of subtitles;
store the first summary and the second summary in a database comprising a plurality of entries, wherein the plurality of entries associates one or more summaries with one or more subjects;
receive a first audio segment of the video conference;
generate a first subtitle comprising a plurality of words using the first audio segment, wherein the first subtitle corresponds to the first audio segment;
select a word of the plurality of words;
access the database comprising the plurality of entries;
determine that a first entry of the plurality of entries associates the selected word with the first subject; and
display the first subtitle, the first summary, the second summary, and the video conference on a screen of a first device at the same time, wherein:
the first subtitle and the first summary are displayed in a first format;
the second summary is displayed in a second format; and
the first format is different than the second format.
16. The non-transitory computer-readable medium of claim 15 , wherein the control circuitry is further caused to:
receive a second audio segment of the video conference;
generate a second subtitle comprising a second plurality of words using the second audio segment, wherein the second subtitle corresponds to the second audio segment;
select a word of the second plurality of words;
access the database;
determine that a second entry of the plurality of entries associates the selected word of the second plurality of words with the second subject; and
display the second subtitle, the second summary, the first summary, and the video conference on the screen of the first device at the same time.
17. The non-transitory computer-readable medium of claim 15 , wherein the control circuitry is further caused to generate the first summary using a natural language process algorithm.
18. The non-transitory computer-readable medium of claim 15 , wherein the video conference is a live video conference.