System and method for controlling related video content based on domain specific language models

• US 10,341,744 B2
• Filed: 06/30/2016
• Issued: 07/02/2019
• Est. Priority Date: 06/30/2016
• Status: Active Grant

• Current Assignee: NBC Universal Media LLC (Comcast Corporation)
• Original Assignee: NBC Universal Media LLC (Comcast Corporation)
• Inventors: Gupta, Gaurav, Beckett, William R.
• Primary Examiner(s): Tran, Thai Q
• Assistant Examiner(s): Hasan, Syed Y
• Application Number:
  US15/199,641
• Publication Number:
  US 20180007448A1
• Time in Patent Office: 1,097 Days
• Field of Search: 386241, 704233, 704235, 704253, 704254, 704260
• CPC Class Codes: G06F 16/433 using audio data
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 25/87 Detection of discrete points within a voice signal
• CPC Class Codes: G11B 27/10 Indexing; Addressing; Timing or synchronising; Measuring tape travel
• CPC Class Codes: G11B 27/105 of operating discs
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence
• CPC Class Codes: G11B 27/34 Indicating arrangements indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D
• CPC Class Codes: H04N 21/233 Processing of audio elementary streams monitoring, identification or recognition of audio in broadcast systems H04H60/58
• CPC Class Codes: H04N 21/2358 for generating different versions, e.g. for different recipient devices
• CPC Class Codes: H04N 21/266 Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
• CPC Class Codes: H04N 21/2665 Gathering content from different sources, e.g. Internet and satellite
• CPC Class Codes: H04N 21/4622 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 Class Codes: H04N 21/4884 for displaying subtitles
• CPC Class Codes: H04N 21/8106 involving special audio data, e.g. different tracks for different languages
• CPC Class Codes: H04N 21/8133 specifically related to the content, e.g. biography of the actors in a movie, detailed information about an article seen in a video program
• CPC Class Codes: H04N 21/8405 represented by keywords
• CPC Class Codes: H04N 5/76 Television signal recording
• CPC Class Codes: H04N 5/91 : Television signal processing therefor
• CPC Class Codes: H04N 9/8205 : involving the multiplexing of an additional signal and the colour video signal

Abstract

Systems and methods for controlling related video content based on domain specific language models are disclosed. Some embodiments include one or more processors configured to obtain a first audio information of first video content, identify first primary time codes based on the first audio information, obtain second audio information of second video content and identify a first secondary plurality of time codes based on the second audio information, determine an amount of differences between the first primary time codes and first secondary time codes, and generate information indicating whether the first video content and the second video content are related based on the determined amount of differences.

Claims

1. A system for controlling related video content, the system comprising:

a memory configured to store information;

one or more processors configured to;

obtain first audio information of first video content from the memory;

identify a first primary plurality of time codes indicating lengths of time between occurrences of a first keyword within the first audio information;

obtain second audio information of second video content from the memory;

identify a first secondary plurality of time codes indicating lengths of time between occurrences of the first keyword within the second audio information;

compare patterns of occurrences of the first keyword in the first video content and the first keyword in the second video content based on the first primary plurality of time codes and the first secondary plurality of time codes; and

generate information indicating whether the first video content and the second video content are related based on the compared patterns; and

output the generated information indicating whether the first video content and the second video content are related, wherein the outputted generated information enables a selection between the first video content or the second video content for storage or display.

2. The system of claim 1, wherein the outputted generated information enables the selection of the first video content or the second video content for display.

3. The system of claim 1, wherein the one or more processors are further configured to identify the first primary plurality of time codes and the second primary plurality of time codes using acoustic keyword spotting based respectively on the first audio information and the second audio information.

4. The system of claim 1, wherein the one or more processors are further configured to identify the first primary plurality of time codes and the second primary plurality of time codes using transcripts generated respectively from the first audio information and the second audio information.

5. The system of claim 1, wherein the one or more processors are further configured to:

identify a second primary plurality of time codes indicating lengths of time between occurrences of a second keyword within the first audio information;

identify a second secondary plurality of time codes indicating lengths of time between occurrences of the second keyword within the second audio information; and

compare additional patterns of occurrences of the second keyword in the first video content and the second keyword in the second video content based on the second primary plurality of time codes and the second secondary plurality of time codes;

wherein the generated information is further based on the compared additional patterns.

6. The system of claim 1, wherein the one or more processors are further configured to identify the first keyword based on a language model assigned to a type of content corresponding to the first video content.

7. The system of claim 1, wherein the one or more processors are further configured to:

obtain a sample video content of a plurality of sample video content all corresponding to a first type of video content; and

cause the memory to store a first language model comprising a plurality of terms specific to the first type of video content based on text corresponding to audio information of the sample video content.

8. The system of claim 7, wherein the text is obtained from closed captioning data associated with the sample video content.

9. The system of claim 7, wherein the one or more processors are configured to select the plurality of terms to be specific to the first type of video content when a frequency of occurrence of each of the plurality of terms within the sample video content exceeds a predetermined threshold.

10. The system of claim 7, wherein the one or more processors are further configured to identify the first keyword based on the first language model.

11. The system of claim 1, wherein the generated information comprises probability information indicating a probability that the first content and the second content are related.

12. A method of controlling related video content, the method comprising:

obtaining first audio information of first video content;

identifying a first primary plurality of time codes indicating lengths of time between occurrences of a first keyword within the first audio information;

obtaining second audio information of second video content;

identifying a first secondary plurality of time codes indicating lengths of time between occurrences of the first keyword within the second audio information;

comparing patterns of occurrences of the first keyword in the first video content and the first keyword in the second video content based on the first primary plurality of time codes and the first secondary plurality of time codes; and

generating information indicating whether the first video content and the second video content are related based on the compared patterns; and

outputting the generated information indicating whether the first video content and the second video content are related, wherein the outputted generated information enables a selection between the first video content or the second video content for storage or display.

13. The method of claim 12, wherein the outputted generated information enables the selection of the first video content or the second video content for display.

14. The method of claim 12, further comprising identifying the first primary plurality of time codes and the second primary plurality of time codes using acoustic keyword spotting based respectively on the first audio information and the second audio information.

15. The method of claim 12, further comprising identifying the first primary plurality of time codes and the second primary plurality of time codes using transcripts generated respectively from the first audio information and the second audio information.

16. The method of claim 12, further comprising:

identifying a second primary plurality of time codes indicating lengths of time between occurrences of a second keyword within the first audio information;

identifying a second secondary plurality of time codes indicating lengths of time between occurrences of the second keyword within the second audio information; and

comparing additional patterns of occurrences of the second keyword in the first video content and the second keyword in the second video content based on the second primary plurality of time codes and the second secondary plurality of time codes;

wherein the generated information is further based on the compared additional patterns.

17. The method of claim 12, further comprising identifying the first keyword based on a language model assigned to a type of content corresponding to the first video content.

18. The method of claim 12, further comprising:

obtaining a sample video content of a plurality of sample video content all corresponding to a first type of video content;

storing a first language model comprising a plurality of terms specific to the first type of video content based on text corresponding to audio information of the sample video content.

19. The method of claim 18, wherein the text is obtained from closed captioning data associated with the sample video content.

20. The method of claim 18, further comprising selecting the plurality of terms to be specific to the first type of video content when a frequency of occurrence of each of the plurality of terms within the sample video content exceeds a predetermined threshold.

21. The method of claim 18, further comprising identifying the first keyword based on the first language model.

22. The method of claim 12, wherein the generated information comprises probability information indicating a probability that the first content and the second content are related.

23. A machine-readable non-transitory medium having stored thereon machine-executable instructions for:

obtaining first audio information of first video content;

identifying a first primary plurality of time codes indicating lengths of time between occurrences of a first keyword within the first audio information;

obtaining second audio information of second video content;

identifying a first secondary plurality of time codes indicating lengths of time between occurrences of the first keyword within the second audio information;

comparing patterns of occurrences of the first keyword in the first video content and the first keyword in the second video content based on the first primary plurality of time codes and the first secondary plurality of time codes; and

generating information indicating whether the first video content and the second video content are related based on the compared patterns; and

outputting the generated information indicating whether the first video content and the second video content are related, wherein the outputted generated information enables a selection between the first video content or the second video content for storage or display.