Speech recognition and summarization
US-10185711-B1 · Jan 22, 2019 · US
US10600420B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10600420-B2 |
| Application number | US-201715707282-A |
| Country | US |
| Kind code | B2 |
| Filing date | Sep 18, 2017 |
| Priority date | May 15, 2017 |
| Publication date | Mar 24, 2020 |
| Grant date | Mar 24, 2020 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Described herein is a system configured to determine when burst activity (e.g., an activity hotspot) occurs in a conference session, and to associate the burst activity with a speaker that is speaking at a time when the burst activity occurs. Burst activity occurs when a threshold number of notable events (e.g., five, ten, fifty, one hundred, one thousand, etc.) occur within a threshold time period (e.g., ten seconds, thirty seconds, one minute, etc.). In various examples, the thresholds can be established relative to a number of participants in a conference session and/or a duration of a conference session (e.g., a scheduled duration). The system can then communicate data indicating that a threshold number of events occurred while an individual speaker is speaking.
Opening claim text (preview).
What is claimed is: 1. A system comprising: one or more processing units; and a computer-readable medium having encoded thereon computer-executable instructions to cause the one or more processing units to: detect activity that occurs in a conference session comprising live or recorded content causing a computing device to output the live or recorded content, the activity comprising a plurality of notable events generated by one or more users participating in the conference session, the plurality of notable events generated by the one or more users in response to an individual speaker that is speaking in the conference session; determine that the plurality of notable events meets or exceeds a threshold number of notable events within a time period of the conference session; associate the time period with the individual speaker that is speaking; and communicate data indicating that the threshold number of notable events occurred while the individual speaker is speaking. 2. The system of claim 1 , wherein the data indicating that the threshold number of notable events occurred while the individual speaker is speaking comprises a notification associated with an object that represents the conference session. 3. The system of claim 1 , wherein the data indicating that the threshold number of notable events occurred while the individual speaker is speaking comprises a text message or an electronic mail message sent to a device or an account of a user who has subscribed to receive the data. 4. The system of claim 1 , wherein the computer-executable instructions further cause the one or more processing units to: generate a visual element that includes a timeline representing a duration of the conference session, wherein generating the visual element includes tagging one or more time intervals with one or more representations to reflect the speaking of the individual speaker; and generate a graph that includes a representation of the threshold number of notable events that occur within the time period of the conference session. 5. The system of claim 4 , wherein the visual element comprises a stacked view of the one or more possible speakers, wherein each possible speaker is associated with the timeline. 6. The system of claim 1 , wherein the threshold number of notable events are associated with a reaction. 7. The system of claim 1 , wherein the individual speaker is recognized using voice recognition. 8. The system of claim 7 , wherein the computer-executable instructions further cause the one or more processing units to: access metadata associated with the conference session, the metadata identifying one or more possible speakers as designated speakers scheduled to present during the conference session; based at least in part on the metadata, access voice models for individual ones of the one or more possible speakers; and use the voice models to determine one or more time intervals during which the individual speaker of the one or more possible speakers is speaking. 9. The system of claim 7 , wherein the computer-executable instructions further cause the one or more processing units to: access metadata associated with the conference session, the metadata identifying one or more possible speakers as one or more participants that have joined the conference session; based at least in part on the metadata, access voice models for individual ones of the one or more possible speakers; and use the voice models to determine one or more time intervals during which the individual speaker of the one or more possible speakers is speaking. 10. A method comprising: detecting, by one or more processing units, activity that occurs in a conference session comprising live or recorded content causing a computing device to output the live or recorded content, the activity comprising a plurality of notable events generated by one or more users participating in the conference session, the plurality of notable events generated by the one or more users in response to an individual speaker that is speaking in the conference session; determining that the plurality of notable events meets or exceeds a threshold number of notable events within a time period of the conference session thereby indicating an increased amount of activity occurs during the time period; determining that the individual speaker is speaking during the time period; and communicating data that summarizes the increased amount of activity that occurs while the individual speaker is speaking during the time period. 11. The method of claim 10 , wherein the data that summarizes the increased amount of activity that occurs while the individual speaker is speaking during the time period comprises a notification associated with an object that represents the conference session. 12. The method of claim 10 , wherein the data that summarizes the increased amount of activity that occurs while the individual speaker is speaking during the time period comprises a text message or an electronic mail message sent to a device or an account of a user who has subscribed to receive the data. 13. The method of claim 10 , wherein the threshold number of notable events are associated with a reaction. 14. The method of claim 10 , wherein the detecting occurs based on detection parameters defined by a user, the detection parameters specifying at least one of the individual speaker and a type of notable event. 15. A system comprising: one or more processing units; and a computer-readable medium having encoded thereon computer-executable instructions to cause the one or more processing units to: detect activity that occurs in a conference session that includes a broadcast presentation comprising live or recorded content causing a computing device to output the live or recorded content, the activity comprising reactions of an audience to the broadcast presentation; determine that a threshold number of reactions occur within a time period; associate the time period with an individual speaker that is speaking; communicate first data indicating that the threshold number of reactions occurred during the time period while the individual speaker is speaking, the first data including a first amount of information that summarizes what is being spoken by the individual speaker during the time period when the threshold number reactions occur; after a predetermined waiting period has elapsed, determine that a user has not joined the conference session in response to communication of the first data; and communicate second data indicating that the threshold number of reactions occurred during the time period while the individual speaker is speaking, the second data including a second amount of information that summarizes what is being spoken by the individual speaker during the time period when the threshold number of reactions occur, the second amount of information including more information than the first amount of information. 16. The system of claim 15 , wherein the first data is communicated via a first form of communication and the second data is communicated via a second form of communication that is different than the first form of communication. 17. The system of claim 16 , wherein the first form of communication comprises a notification displayed in association with an object that represents the conference session and the second form of communication comprises a text message or an electronic mail message sent to a device or an account of the user. 18. The system of claim 15 , wherein the detecting occurs based on detect
Arrangements for multi-party communication, e.g. for conferences (data switching systems for conference H04L12/18; arrangements for connecting several subscribers to a common circuit, i.e. affording conference facilities H04M3/56; television conferencing systems H04N7/15) · CPC title
User profiles · CPC title
Interoperability with other network applications or services · CPC title
Conducting the conference, e.g. admission, detection, selection or grouping of participants, correlating users to one or more conference sessions, prioritising transmission · CPC title
Electricity · mapped topic
Related publications grouped by family.
Answers are generated from the same data shown on this page.