Coded Domain Audio Analysis

• US 20080249976A1
• Filed: 04/06/2007
• Published: 10/09/2008
• Est. Priority Date: 04/06/2007
• Status: Active Grant

• Current Assignee: WSOU Investments, LLC (WSOU Holdings, LLC)
• Original Assignee: Nokia Corporation
• Inventors: Ojanpera, Juha
• Granted Patent: US 8,543,228 B2
• Time in Patent Office: Days
• US Class Current: 707/1
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G10H 1/0008 Associated control or indicating means
• CPC Class Codes: G10H 2210/076 for extraction of timing, tempo; Beat detection
• CPC Class Codes: G10H 2240/061 MP3, i.e. MPEG-1 or MPEG-2 Audio Layer III, lossy audio compression
• CPC Class Codes: G10H 2240/141 Library retrieval matching, i.e. any of the steps of matching an inputted segment or phrase with musical database contents, e.g. query by humming, singing or playing; the steps may include, e.g. musical analysis of the input, musical feature extraction, query formulation, or details of the retrieval process
• CPC Class Codes: G10H 2250/031 Spectrum envelope processing
• CPC Class Codes: G10L 25/00 Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 muting semiconductor-based amplifiers when some special characteristics of a signal are sensed by a speech detector, e.g. sensing when no signal is present, H03G3/34
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence

Abstract

The present invention provides methods, computer-readable media, and apparatuses for determining a measure a similarity of the audio content of a plurality of files. Quantized samples are converted to energy values from files having audio content with compressed formats. Energy characteristics are determined from the energy values and are matched to obtain a greatest content match for a plurality of delay instances. A selected delay value corresponds to a determined offset between the files for relating the audio content of the files. A degree of similarity is determined to relate the audio content of the files. A frequency spectrum is partitioned into a plurality of frequency bands, and a total energy value is determined for each frequency band. The total energy values are correlated for the files.

Claims

1. A method comprising:

converting quantized samples to energy values from a first file and a second file having audio content with compressed formats;

determining energy characteristics from the energy values for the first file and the second file;

matching the energy characteristics for the first file and the second file to obtain a greatest content match for a plurality of delay instances; and

providing a selected delay value from the plurality of delay instances, the selected delay value corresponding to a determined offset between the first file and the second file for relating the audio content of the two files.

2. The method of claim 1, further comprising:

determining a degree of similarity that relates the audio content of the first file and the second file.

3. The method of claim 1, further comprising:

determining the selected delay value from delay characteristics of the plurality of delay instances.

4. The method of claim 1, further comprising:

sub-sampling a bit stream by determining a limited number of quantized samples to be extracted from the bit stream.

5. The method of claim 1, further comprising:

de-quantizing the quantized samples to obtain de-quantized samples corresponding to amplitude levels.

6. The method of claim 5, further combining:

combining the de-quantized samples from a right channel and a left channel of a stereo audio signal to form the energy values.

7. The method of claim 1, further comprising:

partitioning a frequency spectrum into a plurality of frequency bands; and

determining a total energy value for each said frequency band for the first file and the second file.

8. The method of claim 7, further comprising:

correlating the total energy values for the first file and the second file.

9. The method of claim 1, further comprising:

repeating the steps of matching the energy characteristics and providing the selected delay value by changing a reference file.

10. The method of claim 1, further comprising:

repeating the steps of converting, determining, matching, and providing for a third file having audio content.

11. The method of claim 1, the compression format of the first file and the second file being in compliance with an advanced audio coding (AAC) format.

12. The method of claim 1, the compression format of the first file and the second file being in compliance with a Moving Picture Experts Group (MPEG)-1 Layer III (MP3) format.

13. The method of claim 1, the first file and the second file having different compression formats.

14. The method of claim 1, further comprising:

organizing a data structure containing the first file and the second file based on the degree of similarity.

15. The method of claim 1, the first file and the second file containing multi-media content, the multi-media content comprising the audio content.

16. An apparatus comprising:

an energy collection module configured to determine energy values from quantized samples from a first file and a second file having audio content with compressed formats;

an energy matching module configured to match energy characteristics from the energy values for the first file and the second file to obtain matched energy measures for a plurality of time delay instances; and

an analysis module configured to provide a selected delay value from the matched energy measures of the plurality of time delay instances, the selected delay value corresponding to a determined offset between the first file and the second file.

17. The apparatus of claim 16, the analysis module configured to determine a degree of similarity that relates the audio content of the first file and the second file.

18. A computer-readable medium having computer-executable instructions comprising:

converting quantized samples to energy values from a first file and a second file having audio content with compressed formats;

determining energy characteristics from the energy values for the first file and the second file;

matching the energy characteristics for the first file and the second file to obtain a greatest content match for a plurality of delay instances; and

selecting a selected delay value from the plurality of delay instances, the selected delay value corresponding to a determined offset between the first file and the second file.

19. The computer-readable medium of claim 18, further comprising:

determining a degree of similarity that relates the audio content of the first file and the second file.

20. The computer-readable medium of claim 18, further comprising:

partitioning a frequency spectrum into a plurality of frequency bands; and

determining a total energy value in each said frequency band for the first file and the second file.

21. The computer-readable medium of claim 20, further comprising:

correlating the total energy values for the first file and the second file.

22. An apparatus comprising:

means for converting quantized samples to energy values from a first file and a second file having audio content with compressed formats;

means for determining energy characteristics from the energy values for the first file and the second file;

means for matching the energy characteristics for the first file and the second file to obtain a greatest content match for a plurality of delay instances; and

means for providing a selected delay value from the plurality of delay instances, the selected delay value corresponding to a determined offset between the first file and the second file for relating the audio content of the two files.

23. The apparatus of claim 22, further comprising:

means for determining a degree of similarity that relates the audio content of the first file and the second file.

24. An integrated circuit comprising:

an energy collection component configured to determine energy values from quantized samples from a first file and a second file having audio content with compressed formats;

an energy matching component configured to match energy characteristics from the energy values for the first file and the second file to obtain matched energy measures for a plurality of time delay instances; and

an analysis component configured to provide a selected delay value from the matched energy measures of the plurality of time delay instances, the selected delay value corresponding to a determined offset between the first file and the second file.

25. The integrated circuit of claim 24, the analysis module further configured to determine a degree of similarity that relates the audio content of the first file and the second file.