System and method for detecting highlights in a video program using audio properties

• US 6,973,256 B1
• Filed: 10/30/2000
• Issued: 12/06/2005
• Est. Priority Date: 10/30/2000
• Status: Expired due to Fees

• Current Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Dagtas, Serhan
• Primary Examiner(s): Nguyen, Huy
• Application Number:
  US09/699,605
• Time in Patent Office: 1,863 Days
• Field of Search: 386/46, 386/95, 386/96, 386/111, 386/125, 386/126, 369/30.07, 704/235
• US Class Current: 386/241
• CPC Class Codes: G06F 16/7834 using audio features
• CPC Class Codes: G06F 16/7844 using original textual content or text extracted from visual content or transcript of audio data
• CPC Class Codes: G11B 2220/216 Rewritable discs
• CPC Class Codes: G11B 2220/2562 DVDs [digital versatile discs]; Digital video discs; MMCDs; HDCDs
• 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: H04N 5/76 Television signal recording
• CPC Class Codes: H04N 5/781 on disks or drums
• CPC Class Codes: H04N 5/783 Adaptations for reproducing at a rate different from the recording rate
• CPC Class Codes: H04N 9/8042 involving data reduction

Abstract

There is disclosed an apparatus for detecting program highlights in a video program. The apparatus comprises: 1) a keyword detection circuit for detecting a location of a selected keyword in an audio track of the video program; and 2) an audio signal energy level detection circuit for determining an audio signal energy level of the audio track proximate the detected location of the selected keyword and comparing the audio signal energy level to a predetermined threshold. The audio signal energy level detection circuit, in response to a determination that the audio signal energy level exceeds the predetermined threshold, identifies the detected location of the selected keyword as a program highlight.

Claims

1. For use in a video playback device capable of playing back a video program recorded on a storage medium in said video playback device, an apparatus for detecting program highlights in said video program comprising:

a keyword detection circuit capable of detecting a location of a selected keyword in an audio track of said video program; and

an audio signal energy level detection circuit capable of determining an audio signal energy level of said audio track proximate said detected location of said selected keyword and comparing said audio signal energy level to a predetermined threshold;

wherein said audio signal energy level detection circuit, in response to a determination that said audio signal energy level exceeds said predetermined threshold, identifies said detected location of said selected keyword as a program highlight;

wherein said audio signal energy level detection circuit identifies said detected location of said selected keyword as a program highlight by determining a start point of said program highlight preceding said detected location of said selected keyword and by determining a stop point of said program highlight of said program highlight following said detected location of said selected keyword; and

wherein said apparatus for detecting program highlights varies said location of said start point and said stop point of said program highlight in response to a user input.

2. The apparatus as set forth in claim 1 wherein said keyword detection circuit comprises a closed caption detector capable of capturing closed caption text in said video program and a processor for detecting keywords in said captured closed caption text.

3. The apparatus as set forth in claim 2 wherein said processor detects said keywords in said captured closed caption text by comparing said captured closed caption text to a plurality of keywords stored in a memory associated with said processor.

4. The apparatus as set forth in claim 1 wherein said keyword detection circuit comprises an audio processor capable of executing a speech recognition application program that converts spoken words detected in said audio track to text words and wherein said audio processor is further capable of detecting keywords in said converted text words.

5. The apparatus as set forth in claim 4 wherein said audio processor detects said keywords in said converted text words by comparing said converted text words to a plurality of keywords stored in a memory associated with said processor.

6. The apparatus as set forth in claim 1 wherein said audio signal energy level detection circuit determines said audio signal energy level of said audio track by determining an average audio signal energy level in a window proximate said detected location of said selected keyword.

7. A video playback device comprising:

a storage device capable of storing thereon a plurality of video programs;

video recording circuitry capable of receiving an incoming video program and storing said incoming video program on said storage device; and

an apparatus for detecting program highlights in said incoming video program comprising;

a keyword detection circuit capable of detecting a location of a selected keyword in an audio track of said incoming video program; and

an audio signal energy level detection circuit capable of determining an audio signal energy level of said audio track proximate said detected location of said selected keyword and comparing said audio signal energy level to a predetermined threshold;

wherein said audio signal energy level detection circuit, in response to a determination that said audio signal energy level exceeds said predetermined threshold, identifies said detected location of said selected keyword as a program highlight;

wherein said audio signal energy level detection circuit identifies said detected location of said selected keyword as a program highlight by determining a start point of said program highlight preceding said detected location of said selected keyword and by determining a stop point of said program highlight of said program highlight following said detected location of said selected keyword; and

wherein said apparatus for detecting program highlights varies said location of said start point and said stop point of said program highlight in response to a user input.

8. The video playback device as set forth in claim 7 wherein said keyword detection circuit comprises a closed caption detector capable of capturing closed caption text in said video program and a processor for detecting keywords in said captured closed caption text.

9. The video playback device as set forth in claim 8 wherein said processor detects said keywords in said captured closed caption text by comparing said captured closed caption text to a plurality of keywords stored in a memory associated with said processor.

10. The video playback device as set forth in claim 7 wherein said keyword detection circuit comprises an audio processor capable of executing a speech recognition application program that converts spoken words detected in said audio track to text words and wherein said audio processor is further capable of detecting keywords in said converted text words.

11. The video playback device as set forth in claim 10 wherein said audio processor detects said keywords in said converted text words by comparing said converted text words to a plurality of keywords stored in a memory associated with said processor.

12. The video playback device as set forth in claim 7 wherein said audio signal energy level detection circuit determines said audio signal energy level of said audio track by determining an average audio signal energy level in a window proximate said detected location of said selected keyword.

13. For use in a video playback device capable of playing back a video program recorded on a storage medium in the video playback device, a method for detecting program highlights in the video program comprising the steps of:

detecting a location of a selected keyword in an audio track of the video program;

determining an audio signal energy level of the audio track proximate the detected location of the selected keyword;

comparing the audio signal energy level to a predetermined threshold;

determining if the audio signal energy level exceeds the predetermined threshold;

in response to a determination that the audio signal energy level exceeds the predetermined threshold, identifying the detected location of the selected keyword as a program highlight;

determining a start point of said program highlight preceding said detected location of said selected keyword;

determining a stop point of said program highlight following said detected location of said selected keyword; and

varying said location of said start point and said stop point of said program highlight in response to a user input.

14. The method as set forth in claim 13 wherein the step of detecting a location of a keyword comprises the substeps of:

capturing closed caption text in the video program; and

detecting keywords in the captured closed caption text.

15. The method as set forth in claim 14 wherein the step of detecting keywords in the captured closed caption text comprises the substep of comparing the captured closed caption text to a plurality of keywords stored in a keyword library associated with the video playback device.

16. The method as set forth in claim 13 wherein the step of detecting a location of a keyword comprises the substeps of:

executing a speech recognition application program that converts spoken words detected in the audio track to text words; and

detecting keywords in the converted text words.

17. The method as set forth in claim 16 wherein the step of detecting keywords in the converted text words comprises the substep of comparing the converted text words to a plurality of keywords stored in a keyword library associated with the video playback device.

18. The method as set forth in claim 13 wherein the step of determining the audio signal energy level comprises the substep of determining an average audio signal energy level in a window proximate the detected location of the selected keyword.

19. For use in a video playback device capable of playing back a video program recorded on a storage medium in said video playback device, an apparatus for detecting program highlights in said video program comprising:

an audio signal energy level detection circuit capable of determining an audio signal energy level of N consecutive segments of said audio track and comparing said audio signal energy level to a predetermined thresholds

wherein said audio signal energy level detection circuit, in response to a determination that said audio signal energy level exceeds said predetermined threshold, identifies said detected location of said selected keyword as a program highlight;

wherein said audio signal energy level detection circuit identifies said detected location of said selected keyword as a program highlight by determining a start point of said program highlight preceding said detected location of said selected keyword and by determining a stop point of said program highlight of said program highlight following said detected location of said selected keyword; and

wherein said apparatus for detecting program highlights varies said location of said start point and said stop point of said program highlight in response to a user input.

20. The apparatus as set forth in claim 19 wherein said audio signal energy level detection circuit, in response to a determination that said audio signal energy level exceeds said predetermined threshold, identifies said N consecutive segments as a program highlight.

21. The apparatus as set forth in claim 20 wherein said audio signal energy level detection circuit determines said audio signal energy level of said audio track by determining an average audio signal energy level of said N consecutive segments.