Coded domain audio analysis
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.
1. A method comprising:
accessing a first file and a second file, wherein the first file and the second file include compressed audio content;
collecting compressed audio content samples from the compressed audio content of the first file and from the compressed audio content of the second file;
converting the compressed audio content samples to energy values;
determining energy characteristics from the energy values;
matching the energy characteristics to obtain a greatest content match with respect to a plurality of delay instances; and
selecting a delay value based on the greatest content match, the selected delay value corresponding to an offset between the first file and the second file.
2. The method of claim 1 , further comprising:
determining a degree of similarity that relates content of the first file and the second file; and
displaying at least one of the selected delay value and the degree of similarity.
3. The method of claim 1 , further comprising:
wherein selecting the delay value includes determining the delay value from delay characteristics of the plurality of delay instances.
4. The method of claim 1 , further comprising:
determining a limited number of the compressed audio content samples to be extracted from a bit stream; and
extracting the limited number of the compressed audio content samples from the bitstream.
5. The method of claim 1 , further comprising:
de-quantizing the compressed audio content samples to obtain de-quantized samples corresponding to amplitude levels.
6. The method of claim 5 , further comprising:
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:
replacing the first file or the second file with a reference file; and
repeating the steps of matching the energy characteristics and selecting the delay value based on the reference file.
10. The method of claim 1 , further comprising:
collecting second compressed audio content samples from compressed audio content of a third file;
converting the second compressed audio content samples to second energy values;
determining second energy characteristics from the second energy values;
matching the second energy characteristics to obtain a second greatest content match with respect to a second plurality of delay instances; and
select a second selected delay value from the second plurality of delay instances, the second selected delay value corresponding to an offset between the first file and the third file for relating content of the first file and the third file.
11. The method of claim 1 , wherein the compressed audio content of the first file and the compressed audio content of the second file both conform to an advanced audio coding (AAC) format or a Moving Picture Experts Group (MPEG)-1 Layer III (MP3) format.
12. The method of claim 1 , wherein the compressed audio content of the first file conforms to a first compression format and the compressed audio content of the second file conforms to a second compression format different than the first compression format.
13. The method of claim 1 , further comprising:
organizing a data structure that includes the first file and the second file based on a determined similarity between the first file and the second file.
14. The method of claim 1 , wherein both the first file and the second file include compressed multi-media content.
15. An apparatus comprising:
one or more processors; and
at least one memory storing computer-executable instructions that, with the one or more processors, cause the apparatus to at least:
access a first file and a second file, wherein the first file and the second file both include compressed audio content;
collect compressed audio content samples from the compressed audio content of the first file and from the compressed audio content of the second file,
convert the compressed audio content samples to energy values,
determine energy characteristics from the energy values,
match the energy characteristics to obtain a greatest content match with respect to a plurality of time delay instances, and
select a delay value based on the greatest content match, the selected delay value corresponding to an offset between the first file and the second file.
16. The apparatus of claim 15 , wherein the at least one memory further stores computer-executable instructions that, with the one or more processors, cause the apparatus to:
determine a degree of similarity that relates content of the first file and the second file, and
display at least one of the degree of similarity and the selected delay value.
17. A non-transitory computer-readable medium storing computer-executable instructions that, when executed, cause an apparatus to at least:
access a first file and a second file, wherein the first file and the second file include compressed audio content;
collect compressed audio content samples from the compressed audio content of the first file and from the compressed audio content of the second file;
convert the compressed audio content samples to energy values;
determine energy characteristics from the energy values for the first file and the second file;
match the energy characteristics to obtain a greatest content match with respect to a plurality of delay instances; and
select a delay value based on the greatest content match, the selected delay value corresponding to an offset between the first file and the second file.
18. The non-transitory computer-readable medium of claim 17 , further storing computer-executable instructions that, when executed, cause the apparatus to:
determine a degree of similarity that relates content of the first file and the second file, and
display at least one of the degree of similarity and the selected delay value.
19. The non-transitory computer-readable medium of claim 17 , further storing computer-executable instructions that, when executed, cause the apparatus to:
partition a frequency spectrum into a plurality of frequency bands; and
determine a total energy value in each said frequency band for the first file and the second file.
20. The non-transitory computer-readable medium of claim 19 , further storing computer-executable instructions that, when executed, cause the apparatus to:
correlate the total energy values for the first file and the second file.
21. The non-transitory computer-readable medium of claim 17 , further storing computer-executable instructions that, when executed, cause the apparatus to:
determine a limited number of the compressed audio content samples to be extracted from a bit stream; and
extract the limited number of the compressed audio content samples from the bitstream.
22. The non-transitory computer-readable medium of claim 17 , wherein both the first file and the second file include compressed multi-media content.
23. The apparatus of claim 15 , wherein the at least one memory further stores computer-executable instructions that, with the one or more processors, cause the apparatus to:
determine a limited number of the compressed audio content samples to be extracted from a bit stream; and
extract the limited number of the compressed audio content samples from the bitstream.
24. The apparatus of claim 15 , wherein both the first file and the second file include multi-media content.
25. The method of claim 1 , wherein collecting the compressed audio content samples includes collecting a portion of the compressed audio content samples at a rate dependent on one or more encoding properties of the first file, wherein the encoding properties include a frame size used to encode the first file and a sampling rate used to encode the first file.
26. The method of claim 1 , wherein the delay value is in a block domain based on a compression format of the first file or a compression format of the second file.