Crowdsourcing-enhanced audio

Patent metadata

Field	Value
Publication number	US-9749708-B2
Application number	US-201514942650-A
Country	US
Kind code	B2
Filing date	Nov 16, 2015
Priority date	Nov 16, 2015
Publication date	Aug 29, 2017
Grant date	Aug 29, 2017

Abstract

Crowdsourcing techniques may be used to enhance the experience of users viewing and/or listening to content (e.g., live and/or pre-recorded content, such as movies, sporting events, etc.). A server device may analyze audio, captured by multiple user devices, in order to determine trigger points, in the content. The trigger point may be a time point in the content, at which the captured audio, received from multiple user devices, should be played by subsequent user devices that play back the content.

First claim

What is claimed is:

1. A device, comprising:
one or more memory devices storing processor-executable instructions; and
one or more processors configured to execute the processor-executable instructions, wherein executing the processor-executable instructions causes the one or more processors to:
receive, from a plurality of user devices, local audio information pertaining to a particular content item, wherein a particular instance of local audio information, received from a particular user device, includes:
local audio, captured by the particular user device, during playback of the particular content item; and
information indicating a particular time position, in the particular content item, at which the local audio was captured;

determine, based on the received local audio information, from the plurality of user devices, that the particular time position in the particular content item is associated with a trigger event, wherein when determining, that the particular time position in the particular content item is associated with the trigger event, the device is further configured to:
determine a first quantity of user devices that have received or presented the particular content item;
determine that a second quantity of instances of local audio information, received from the plurality of user devices, that correspond to the particular time position in the particular content item, exceeds a threshold quantity; and
determine that a ratio of the second quantity to the first quantity exceeds a threshold ratio;

generate or modify, based on the determination that the particular time position is associated with the trigger event, an audio track, including the local audio, captured by at least two user devices, of the plurality of user devices; and
provide the audio track to another user device that has received the particular content item, wherein the other user device plays the generated audio track, while playing the particular content item, at the particular time position in the particular content item.

2. The device of claim 1 , wherein the threshold quantity is a first threshold quantity,
wherein executing the processor-executable instructions, to determine that the particular time position in the particular content item is associated with the trigger event, further causes the one or more processors to:
determine that a quantity of instances of local audio information, received from the plurality of user devices, that correspond to the particular time position in the particular content item, exceeds a second threshold quantity.

3. The device of claim 1 , wherein the particular user device is a first user device, wherein executing the processor-executable instructions further causes the one or more processors to:
detect speech in local audio received from a second user device, the speech having been captured at the particular time position in the particular content item; and
omit the local audio, received from the second user device, when determining that the particular time position in the particular content item is associated with the trigger event, the omitting being based on the local audio from the second user device including speech.

4. The device of claim 1 , wherein executing the processor-executable instructions further causes the one or more processors to:
detect that the local audio, received from the particular user device, includes a non-speech utterance, the local audio having been captured at the particular time position in the particular content item.

5. The device of claim 1 , wherein executing the processor-executable instructions, to generate or modify the audio track, further causes the one or more processors to:
normalize a volume of the local audio, captured by the at least two user devices.

6. The device of claim 1 , wherein executing the processor-executable instructions further causes the one or more processors to:
receive an indication that the other user device is presenting the particular content item, and that a current time position, during the presenting of the particular content item, is within a threshold time of the particular time position associated with the trigger event,
wherein the providing of the audio track is performed based on the indication that the other user device is presenting the particular content item, and that the current time position, during the presenting of the particular content item, is within the threshold time of the particular time position associated with the trigger event.

7. The device of claim 1 , wherein executing the processor-executable instructions further causes the one or more processors to:
receive an indication that the other user device has downloaded the particular content item for offline viewing,
wherein the providing of the audio track is performed based on the indication that the other user device has downloaded the particular content item for offline viewing.

8. A method, comprising:
receiving, by one or more server devices and from a plurality of user devices, local audio information pertaining to a particular content item, wherein a particular instance of local audio information, received from a particular user device, includes:
local audio, captured by the particular user device, during playback of the particular content item; and
information indicating a particular time position, in the particular content item, at which the local audio was captured;

determining, by the one or more server devices and based on the received local audio information, from the plurality of user devices, that the particular time position in the particular content item is associated with a trigger event, wherein determining, that the particular time position in the particular content item is associated with the trigger event, includes:
determining a first quantity of user devices that have received or presented the particular content item;
determining that a second quantity of instances of local audio information, received from the plurality of user devices, that correspond to the particular time position in the particular content item, exceeds a threshold quantity; and
determining that a ratio of the second quantity to the first quantity exceeds a threshold ratio;

generating or modifying, by the one or more server devices and based on the determination that the particular time position is associated with the trigger event, an audio track, including the local audio, captured by at least two user devices, of the plurality of user devices; and
providing, by the one or more server devices, the audio track to another user device that has received the particular content item, wherein the other user device plays the generated audio track, while playing the particular content item, at the particular time position in the particular content item.

9. The method of claim 8 , wherein the threshold quantity is a first threshold quantity,
wherein determining, that the particular time position in the particular content item is associated with the trigger event, includes:
determining that a quantity of instances of local audio information, received from the plurality of user devices, that correspond to the particular time position in the particular content item, exceeds a second threshold quantity.

10. The method of claim 8 , wherein the particular user device is a first user device, the method further comprising:
detecting speech in local audio received from a second user device, the speech having been captured at the particular time position in the particular content item; and
omitting the local audio, received from the second user device, when determining that the particular time position in the particular content item is as

Assignees

• Verizon Patent & Licensing Inc

Inventors

• Blong Devin
• Flores Kevin
• Chaudhary Tushar
• Sharma Manish

Classifications

• H04N21/44213

  Monitoring of end-user related data (arrangements for monitoring the users' behaviour or opinions in broadcast systems H04H60/33) · CPC title

• H04N21/4622

  Retrieving content or additional data from different sources, e.g. from a broadcast channel and the Internet (web site content organization and management for information retrieval from the Internet G06F16/958; transmission by internet of broadcast information H04H60/82; stock exchange data over packet-switching network H04L12/1804; push services including data channel over packet-switching network H04L12/1859) · CPC title

• H04N21/439

  Processing of audio elementary streams · CPC title

• H04N21/42203

  sound input device, e.g. microphone · CPC title

• H04N21/475

  End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data · CPC title