Multimedia information retrieval method and electronic device

• US 9,704,485 B2
• Filed: 02/04/2015
• Issued: 07/11/2017
• Est. Priority Date: 08/24/2012
• Status: Active Grant

• Current Assignee: Tencent Technology Company Limited (Tencent Holdings Limited)
• Original Assignee: Tencent Technology Company Limited (Tencent Holdings Limited)
• Inventors: Hu, Peng, Zhang, Teng
• Primary Examiner(s): Yen, Eric
• Application Number:
  US14/613,989
• Publication Number:
  US 20150154958A1
• Time in Patent Office: 888 Days
• 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: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G10L 15/05 Word boundary detection
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

The present invention relates to a multimedia information retrieval method and electronic device, the multimedia information retrieval method comprising the steps of: extracting from a to-be-retrieved multimedia the voice of the to-be-retrieved multimedia; recognizing the voice of the to-be-retrieved multimedia to obtain a recognized text; and retrieving a multimedia database according to the recognized text to obtain the multimedia information of the to-be-retrieved multimedia. The present invention also relates to an electronic device. The multimedia information retrieval method and electronic device of the present invention can automatically, quickly, and comprehensively present to a user the multimedia information the user wants to know, thus greatly improving user retrieval efficiency and retrieval success rate.

Claims

1. A multimedia information retrieval method, comprising steps of:

extracting a voice of multimedia to be retrieved from multimedia to be retrieved;

recognizing the voice of the multimedia to be retrieved to obtain a recognized text; and

retrieving multimedia information of the multimedia to be retrieved in a multimedia database according to the recognized text, wherein, retrieving multimedia information of the multimedia to be retrieved in the multimedia database according to the recognized text comprises;

performing word segmentation on the recognized text according to a preset word library to obtain a plurality of undetermined recognition codes;

determining a plurality of recognition codes according to word occurrence frequencies of the undetermined recognition codes in the word library; and

retrieving the plurality of recognition codes in the multimedia database to obtain the multimedia information of the multimedia to be retrieved.

2. The method according to claim 1, wherein, the undetermined recognition codes comprise at least one of Chinese characters, Pinyin or English words.

3. The method according to claim 1, wherein determining the plurality of recognition codes according to the word occurrence frequencies of the undetermined recognition codes in the word library comprises:

selecting n undetermined recognition codes with the lowest word occurrence frequencies in the word library from the plurality of undetermined recognition codes;

randomly selecting m undetermined recognition codes, wherein each one of the n undetermined recognition codes is different from any one of the m undetermined recognition codes; and

setting the n undetermined recognition codes and the m undetermined recognition codes as the plurality of recognition codes, wherein n is equal to or larger than 1, and m is equal to or larger than 0.

4. The method according to claim 1, further comprising a step of:

presenting the multimedia information to a user, wherein the multimedia information comprises at least one of song title, singer, song lyrics, album, background information, music score, or download link for the multimedia.

5. An electronic device, comprising:

one or more processors;

a storage; and

one or more computer programs stored on the storage and configured to cause the one or more processors to perform a multimedia information retrieval method, wherein the one or more computer programs comprise;

a voice extracting module configured to extract a voice of multimedia to be retrieved from multimedia to be retrieved;

a voice recognizing module configured to recognize the voice of the multimedia to be retrieved to obtain a recognized text; and

a retrieving module configured to retrieve multimedia information of the multimedia to be retrieved in a multimedia database according to the recognized text, wherein the retrieving module further comprises;

an undetermined recognition code determining unit configured to perform word segmentation on the recognized text according to a preset word library to obtain a plurality of undetermined recognition codes;

a recognition code determining unit configured to determine a plurality of recognition codes according to word occurrence frequencies of the undetermined recognition codes in the word library; and

a retrieving unit configured to retrieve the recognition codes in the multimedia database to obtain the multimedia information of the multimedia to be retrieved.

6. The electronic device according to claim 5, wherein, the undetermined recognition codes comprise at least one of Chinese characters, Pinyin or English words.

7. The electronic device according to claim 5, wherein, the recognition code determining unit is configured to:

select n undetermined recognition codes with the lowest word occurrence frequencies in the word library from the plurality of undetermined recognition codes;

randomly select m undetermined recognition codes, so that each one of the n undetermined recognition codes is different from any one of the m undetermined recognition codes; and

set the n undetermined recognition codes and the m undetermined recognition codes as the plurality of recognition codes, wherein n is equal to or larger than 1, and m is equal to or larger than 0.

8. The electronic device according to claim 5, wherein the one or more computer programs further comprise:

a multimedia presenting module configured to present the multimedia information to a user, wherein the multimedia information comprises at least one of song title, singer, song lyrics, album, background information, music score, or download link for the multimedia.

9. An electronic device, comprising:

one or more processors;

a storage; and

one or more computer programs stored on the storage and configured to cause the one or more processors to provide a multimedia information retrieval method, wherein the one or more computer programs comprise;

a multimedia database configured to store multimedia information;

a download module configured to download multimedia to be retrieved by a download link for the multimedia to be retrieved;

a voice extracting module configured to extract a voice of the multimedia to be retrieved from the multimedia to be retrieved;

a voice recognizing module configured to recognize the voice of the multimedia to be retrieved to obtain a recognized text; and

a retrieving module configured to retrieve multimedia information of the multimedia to be retrieved in the multimedia database according to the recognized, wherein the retrieving module comprises;

an undetermined recognition code determining unit configured to perform word segmentation on the recognized text according to a preset word library to obtain a plurality of undetermined recognition codes;

a recognition code determining unit configured to determine a plurality of recognition codes according to word occurrence frequencies of the undetermined recognition codes in the word library; and

a retrieving unit configured to retrieve the recognition codes in the multimedia database to obtain the multimedia information of the multimedia to be retrieved.

10. The electronic device according to claim 9, wherein, the undetermined recognition codes comprise at least one of Chinese characters, Pinyin and English words.

11. The electronic device according to claim 9, wherein, the recognition code determining unit is configured to:

select n undetermined recognition codes with the lowest word occurrence frequencies in the word library from the plurality of undetermined recognition codes;

randomly select m undetermined recognition codes, so that each one of the n undetermined recognition codes is different from any one of the m undetermined recognition codes; and

set the n undetermined recognition codes and the m undetermined recognition codes as the plurality of recognition codes, wherein n is equal to or larger than 1, and m is equal to or larger than 0.

12. The electronic device according to claim 9, wherein, the one or more computer programs further comprise a feedback module configured to return the multimedia information of the multimedia to be retrieved to a user, wherein the multimedia information of the multimedia to be retrieved comprises at least one of song title, singer, song lyrics, album, background information, music score, or download link for the multimedia.

13. The electronic device according to claim 9, wherein, the one or more computer programs further comprise an associating module configured to associate the download link for the multimedia to be retrieved with the multimedia information of the multimedia to be retrieved.