Methods and apparatus for audio recognition
First Claim
Patent Images
1. An apparatus for generating an audio fingerprint, comprising:
- a processor operable to;
extract a plurality of frequencies from two or more audio source files included in a set of audio source files, wherein the two or more audio source files are encoded in different formats;
measure, across the two or more audio source files, a range of variation of each of the plurality of frequencies, the range of variation of a respective frequency being a range of variation of values for the frequency measured from among the two or more audio source files;
for each of the plurality of frequencies, compare the range of variation to a corresponding threshold to determine whether the range of variation is less than the corresponding threshold;
identify a plurality of stable frequencies from among the plurality of frequencies extracted from two or more audio source files, an extracted frequency being identified as a stable frequency if the respective range of variation is determined to be less than the corresponding threshold;
identify harmonically related stable frequencies from among the identified plurality of stable frequencies, each group of harmonically related stable frequencies forming a stable frequency family;
map sample points of an unknown recording to at least a portion of at least one stable frequency family;
generate fingerprint data by analyzing the mapped sample points of the unknown recording; and
form the audio fingerprint from the generated fingerprint data.
12 Assignments
0 Petitions
Accused Products
Abstract
Frequencies from a set of audio source files are extracted and measured across the set to determine a range of each of the frequencies. Stable frequencies of the frequencies are detected based on each range and used to create a stable frequency family. An unknown recording is mapped to the stable frequency family to form an audio fingerprint.
-
Citations
20 Claims
-
1. An apparatus for generating an audio fingerprint, comprising:
-
a processor operable to; extract a plurality of frequencies from two or more audio source files included in a set of audio source files, wherein the two or more audio source files are encoded in different formats; measure, across the two or more audio source files, a range of variation of each of the plurality of frequencies, the range of variation of a respective frequency being a range of variation of values for the frequency measured from among the two or more audio source files; for each of the plurality of frequencies, compare the range of variation to a corresponding threshold to determine whether the range of variation is less than the corresponding threshold; identify a plurality of stable frequencies from among the plurality of frequencies extracted from two or more audio source files, an extracted frequency being identified as a stable frequency if the respective range of variation is determined to be less than the corresponding threshold; identify harmonically related stable frequencies from among the identified plurality of stable frequencies, each group of harmonically related stable frequencies forming a stable frequency family; map sample points of an unknown recording to at least a portion of at least one stable frequency family; generate fingerprint data by analyzing the mapped sample points of the unknown recording; and form the audio fingerprint from the generated fingerprint data. - View Dependent Claims (2, 3, 4, 5, 6, 19)
-
-
7. A method for generating an audio fingerprint, comprising:
-
extracting, using an audio processor, a plurality of frequencies from two or more audio source files include in a set of audio source files, wherein the two or more audio source files are encoded in different formats; measuring, across the two or more audio source files, a range of variation of each of the plurality of frequencies, the range of variation of a respective frequency being a range of variation of values for the frequency measured from among the two or more audio source files; for each of the plurality of frequencies, comparing the range to a corresponding threshold to determine whether the range of variation is less than the corresponding threshold; identifying a plurality of stable frequencies from among the plurality of frequencies extracted from two or more audio source files, an extracted frequency being identified as a stable frequency if the respective range of variation is determined to be less than the corresponding threshold; identifying harmonically related stable frequencies from among the identified plurality of stable frequencies, each group of harmonically related stable frequencies forming a stable frequency family; mapping sample points of an unknown recording to at least a portion of at least one stable frequency family; generating fingerprint data by analyzing the mapped sample points of the unknown recording; and forming the audio fingerprint from the generated fingerprint data. - View Dependent Claims (8, 9, 10, 11, 12, 20)
-
-
13. A non-transitory computer-readable medium having stored thereon sequences of instructions, the sequences of instructions including instructions which when executed by a computer system causes the computer system to perform:
-
extracting, using an audio processor, a plurality of frequencies from two or more audio source files included in a set of audio source files, wherein the two or more of the audio source files are encoded in different formats; measuring, across the two or more audio source files, a range of variation of each of the plurality of frequencies, the range of variation of a respective frequency being a range of variation of values for the frequency measured from among the two or more audio source files; for each of the plurality of frequencies, comparing the range of variation to a corresponding threshold to determine whether the range of variation is less than the corresponding threshold identifying a plurality of stable frequencies from among the plurality of frequencies extracted from two or more audio source files, an extracted frequency being identified as a stable frequency if the respective range of variation is determined to be less than the corresponding threshold; identifying harmonically related stable frequencies from among the identified plurality of stable frequencies, each group of harmonically related stable frequencies forming a stable frequency family; mapping sample points of an unknown recording to at least a portion of at least one stable frequency family generating fingerprint data by analyzing the mapped sample points of the unknown recording; and forming the audio fingerprint from the generated fingerprint data. - View Dependent Claims (14, 15, 16, 17, 18)
-
Specification