Method of generating audiovisual content through meta-data analysis

• US 20100023485A1
• Filed: 07/25/2008
• Published: 01/28/2010
• Est. Priority Date: 07/25/2008
• Status: Abandoned Application

• Current Assignee: Cyberlink Corporation
• Original Assignee: Cyberlink Corporation
• Inventors: Cheng Chu, Hung-Yi
• Application Number:
  US12/179,585
• Publication Number:
  US 20100023485A1
• Time in Patent Office: Days
• US Class Current: N/A
• CPC Class Codes: G06F 16/433 using audio data
• CPC Class Codes: G06F 16/434 using image data, e.g. images, photos, pictures taken by a user
• CPC Class Codes: G06F 16/4393 Multimedia presentations, e.g. slide shows, multimedia albums

Abstract

To provide fast, robust matching of audio content, such as music, with visual content, such as images, videos, and text, a keyword is extracted from either the audio content or the visual content. The keyword is then utilized to match the audio content with the visual content, or the visual content with the audio content. The keyword may also be utilized to find other related keywords for expanding the amount of visual content or audio content matched. The matched audio and visual content may also be mixed to generate audiovisual content, such as a presentation or slideshow with background music.

Claims

1. A method of matching audio content with visual content, the method comprising:

decoding meta-data of the audio content;

extracting a keyword from the meta-data of the audio content;

matching the visual content to the audio content when the keyword corresponds to the visual content; and

generating audiovisual content by mixing the audio content and the visual content.

2. The method of claim 1, further comprising:

ignoring text information other than the keyword when extracting the keyword from the audio content.

3. The method of claim 2, further comprising:

searching for the text information in a vocabulary database;

wherein ignoring the text information other than the keyword is ignoring the text information other than the keyword when the text information is found in the vocabulary database.

4. The method of claim 1, further comprising:

searching for a related keyword corresponding to the keyword; and

matching the visual content to the audio content when the related keyword corresponds to the visual content.

5. The method of claim 4, wherein searching for the related keyword is receiving the related keyword from an Internet-based search of the keyword.

6. The method of claim 5, wherein receiving the related keyword from the Internet-based search is extracting a user-generated comment or tag from a result of the Internet-based search.

7. The method of claim 4, wherein searching for the related keyword is searching for the related keyword in a vocabulary database.

8. The method of claim 1, further comprising:

searching for the visual content according to the keyword before matching the visual content to the audio content.

9. The method of claim 1, further comprising:

searching for lyrics corresponding to the audio content;

extracting a lyric keyword from the lyrics; and

matching the visual content to the audio content when the lyric keyword corresponds to the visual content.

10. The method of claim 1, further comprising:

extracting a keyword from the visual content;

wherein matching the visual content to the audio content when the keyword corresponds to the visual content is matching the visual content to the audio content when the keyword extracted from the audio content matches the keyword extracted from the meta-data of the visual content.

11. The method of claim 1, wherein matching the visual content to the audio content when the keyword corresponds to the visual content is matching at least one image to the audio content when the keyword corresponds to the at least one image.

12. The method of claim 1, wherein matching the visual content to the audio content when the keyword corresponds to the visual content is matching text to the audio content when the keyword corresponds to the text.

13. The method of claim 12, wherein matching the text to the audio content when the keyword corresponds to the text is matching a quote to the audio content when the keyword is a word of the quote.

14. The method of claim 1, further comprising playing the audiovisual content.

15. A method of matching visual content with audio content, the method comprising:

decoding meta-data from the visual content;

extracting a keyword from the meta-data;

matching the audio content to the visual content when the keyword corresponds to the audio content; and

generating audiovisual content by mixing the visual content and the audio content.

16. The method of claim 15, further comprising:

ignoring text information other than the keyword when extracting the keyword from the visual content.

17. The method of claim 16, further comprising:

searching for the text information in a vocabulary database;

wherein ignoring the text information other than the keyword is ignoring the text information other than the keyword when the text information is found in the vocabulary database.

18. The method of claim 15, further comprising:

searching for a related keyword corresponding to the keyword; and

matching the audio content to the visual content when the related keyword corresponds to the audio content.

19. The method of claim 18, wherein searching for the related keyword is receiving the related keyword from an Internet-based search of the keyword.

20. The method of claim 19, wherein receiving the related keyword from the Internet-based search is extracting a user-generated comment or tag from a result of the Internet-based search.

21. The method of claim 18, wherein searching for the related keyword is searching for the related keyword in a vocabulary database.

22. The method of claim 15, further comprising:

searching for the audio content according to the keyword before matching the audio content to the visual content.

23. The method of claim 15, further comprising:

searching for lyrics corresponding to the audio content;

extracting a lyric keyword from the lyrics; and

matching the audio content to the visual content when the lyric keyword corresponds to the keyword.

24. The method of claim 15, wherein matching the audio content to the visual content when the keyword corresponds to the audio content is matching at least one song to the visual content when the keyword corresponds to the at least one song.

25. The method of claim 15, further comprising:

extracting a keyword from meta-data of the audio content;

wherein matching the audio content to the visual content when the keyword corresponds to the audio content is matching the audio content to the visual content when the keyword extracted from the visual content matches the keyword extracted from the meta-data of the audio content.

26. The method of claim 15, further comprising playing the audiovisual content.