DEVICE, METHOD, AND MEDIUM FOR GENERATING AUDIO FINGERPRINT AND RETRIEVING AUDIO DATA

• US 20130132210A1
• Filed: 01/16/2013
• Published: 05/23/2013
• Est. Priority Date: 11/11/2005
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: She, Yuan Yuan, Eom, Kiwan, Zhu, Xuan, Kim, Jiyeun, KIM, Hyounggook
• Granted Patent: US 9,589,283 B2
• Time in Patent Office: Days
• US Class Current: 705/14.72
• CPC Class Codes: G06Q 30/0276 Advertisement creation
• CPC Class Codes: G10L 19/0212 using orthogonal transformation
• CPC Class Codes: G10L 25/48 specially adapted for particular use

Abstract

Provided are device, method, and medium for generating an audio fingerprint and retrieving audio data. The device for generating an audio fingerprint includes: a coefficient extracting section partially decoding audio data in a compression area and extracting MDCT (Modified Discrete Cosine Transform) coefficients; a coefficient selecting section selecting an MDCT coefficient robust to noises from the extracted MDCT coefficients; a modulation spectrum generating section transforming the selected MDCT coefficient by the use of a Fourier transform method and generating a modulation spectrum; and a bit conversion section quantizing the generated modulation spectrum and generating an audio fingerprint. As a result, it is possible to accurately and rapidly retrieve the audio data recorded in a variety of environments. Since elements based on MP3 are used, it is possible to apply to MP3 applications in various manners. In addition, it is possible to apply to classification of audio data such as classification of music moods and classification of music genres and various other fields such as extraction of a specific event from moving images of sports.

Claims

1. A method of showing information related to an advertisement using audio data of the advertisement comprising:

obtaining a segment of the audio data;

generating an audio fingerprint from the obtained segment;

searching the information related to the advertisement by using the generated audio fingerprint; and

showing the searched information related to the advertisement.

2. The method of claim 1, wherein the segment is obtained in a device connected to a network.

3. The method of claim 2, wherein the audio fingerprint is generated by considering characteristics of the audio data so that the fingerprint is robust to noise.

4. The method of claim 1, wherein the searching the information comprises:

extracting the information corresponding to the generated audio fingerprint from a database storing information related to the audio data by using a conversion value of the generated audio fingerprint.

5. The method of claim 4, wherein the extracting the information comprises:

generating a hashing value using the generated audio fingerprint;

retrieving the hashing value matched with the generated hashing value from a hashing table storing hashing values corresponding to fingerprints; and

extracting the information corresponding to the retrieved hashing value from a database storing information related to audio data.

6. The method of claim 1, further comprising:

transmitting the obtained segment to a search medium;

wherein the generating the audio fingerprint comprises generating the audio fingerprint using the transmitted segment.

7. The method of claim 1, further comprising:

transmitting the generated audio fingerprint to a search medium;

wherein the searching the information comprises searching the information using the transmitted audio fingerprint.

8. The method of claim 1, further comprising:

transmitting the searched information to a output medium;

wherein the outputting the information comprises outputting the transmitted information.

9. The method of claim 1, wherein the audio data comprises at least one of background music and narration included in the advertisement.

10. A non-transitory computer readable recording medium having recorded thereon a program for executing the method of claim 1.

11. A processor for showing information related to an advertisement using audio data of the advertisement is configured to:

obtain a segment of the audio data;

generate an audio fingerprint from the obtained segment;

search the information related to the advertisement using the generated audio fingerprint; and

show the searched information related to the advertisement.

12. The processor of claim 11, wherein the segment is obtained in a device connected to a network.

13. The processor of claim 12, wherein the audio fingerprint is generated by considering characteristics of the audio data so that the fingerprint is robust to noise.

14. The processor of claim 11, wherein the processor is configured to:

extract the information corresponding to the generated audio fingerprint from a database storing information related to the audio data using a conversion value of the generated audio fingerprint.

15. The processor of claim 14, wherein the processor is configured to:

generate a hashing value using the generated audio fingerprint;

retrieve the hashing value matched with the generated hashing value from a hashing table storing hashing values corresponding to fingerprints; and

extract the information corresponding to the retrieved hashing value from a database storing information related to audio data.

16. The processor of claim 11, wherein the processor is configured to:

transmit the obtained segment to a search unit;

wherein the generating the audio fingerprint comprises generating the audio fingerprint using the transmitted segment.

17. The processor of claim 11, wherein the processor is configured to:

transmit the generated audio fingerprint to a search unit;

wherein the searching the information comprises searching the information using the transmitted audio fingerprint.

18. The processor of claim 11, wherein the processor is configured to:

transmit the searched information to a output unit;

wherein the outputting the information comprises outputting the transmitted information.

19. The processor of claim 11, wherein the audio data comprises at least one of background music and narration included in the advertisement.