Audio matching with semantic audio recognition and report generation
View Patent ↗System, apparatus and method for determining semantic information from audio, where incoming audio is sampled and processed to extract audio features, including temporal, spectral, harmonic and rhythmic features. The extracted audio features are compared to stored audio templates that include ranges and/or values for certain features and are tagged for specific ranges and/or values. The semantic information may be associated with audio signature data Extracted audio features that are most similar to one or more templates from the comparison are identified according to the tagged information. The tags are used to determine the semantic audio data that includes genre, instrumentation, style, acoustical dynamics, and emotive descriptor for the audio signal.
1. A processor-based method for producing supplemental information for audio signature data, the method comprising:
obtaining, by executing instructions with a processor, the audio signature data of a first time period, the audio signature data including data relating to at least one of time or frequency components representing a first characteristic of media;
obtaining, by executing instructions with the processor, first semantic audio signature data for the first time period, the first semantic audio signature data being a measure of generalized information representing characteristics of the media; and
storing, in a memory, the audio signature data of the first time period in association with a second time period when the processor determines, by executing instructions with the processor, that second semantic audio signature data for the second time period substantially matches the first semantic audio signature data for the first time period.
2. The method of claim 1 , wherein the measure of generalized information representing characteristics of the media includes a timber feature having at least one of a mean of a spectral centroid, a variance of the spectral centroid, or a percentage of low/high energy frames.
3. The method of claim 1 , wherein the measure of generalized information representing characteristics of the media includes a beat feature having at least one of an amplitude of peaks in a beat histogram, a period of peaks in the beat histogram, or a ratio between a peak and a sum of all peaks in the beat histogram.
4. The method of claim 1 , wherein the measure of generalized information representing characteristics of the media includes a pitch feature having at least one of an amplitude of prominent peaks in a pitch histogram, or a period of peaks in the pitch histogram, where the pitch histogram is on a full semitone scale or an octave independent scale.
5. The method of claim 1 , wherein the first semantic audio signature data includes at least one of a temporal feature, a spectral feature, a harmonic feature, or a rhythmic feature.
6. The method of claim 1 , wherein the audio signature data is generated by transforming an audio signal of the media from a time domain to a frequency domain.
7. The method of claim 1 , wherein the first semantic audio signature data is generated by transforming an audio signal of the media from a time domain to a frequency domain.
8. An apparatus for producing supplemental information for audio signature data, the apparatus including:
a processor to:
obtain the audio signature data of a first time period, the audio signature data including data relating to at least one of time or frequency components representing a first characteristic of media;
obtain first semantic audio signature data for the first time period, the first semantic audio signature data being a measure of generalized information representing characteristics of the media; and
memory to store the audio signature data of the first time period in association with a second time period when the processor determines that second semantic audio signature data for the second time period substantially matches the first semantic audio signature data for the first time period.
9. The apparatus of claim 8 , wherein the measure of generalized information representing characteristics of the media includes a timber feature having at least one of a mean of a spectral centroid, a variance of the spectral centroid, or a percentage of low/high energy frames.
10. The apparatus of claim 8 , wherein the measure of generalized information representing characteristics of the media includes a beat feature having at least one of an amplitude of peaks in a beat histogram, a period of peaks in the beat histogram, or a ratio between a peak and a sum of all peaks in the beat histogram.
11. The apparatus of claim 8 , wherein the measure of generalized information representing characteristics of the media includes a pitch feature having at least one of an amplitude of prominent peaks in a pitch histogram, or a period of peaks in the pitch histogram, where the pitch histogram is on a full semitone scale or an octave independent scale.
12. The apparatus of claim 8 , wherein the first semantic audio signature data includes at least one of a temporal feature, a spectral feature, a harmonic feature, or a rhythmic feature.
13. The apparatus of claim 8 , wherein the audio signature data is generated by transforming an audio signal of the media from a time domain to a frequency domain.
14. The apparatus of claim 8 , wherein the first semantic audio signature data is generated by transforming an audio signal of the media from a time domain to a frequency domain.
15. A processor-based method for producing supplemental information for audio signature data, the method comprising:
obtaining, by executing instructions with a processor, the audio signature data at an input from a data network, the audio signature data received from a device, the audio signature data including data relating to at least one of time or frequency components representing a first characteristic of media;
obtaining, by executing instructions with the processor, semantic audio signature data at the input from the data network, the semantic audio signature data received from the device, the semantic audio signature data being a measure of at least one of a timber feature, a beat feature or a pitch feature relating to a second characteristic of the media;
associating, by executing instructions with the processor, the semantic audio signature data to the audio signature data; and
processing, by executing instructions with the processor, the associated semantic audio signature data and audio signature data to determine a change in the second characteristic relative to the first characteristic.
16. The method of claim 15 , wherein the timber feature includes one of a mean of a spectral centroid, a variance of the spectral centroid, or a percentage of low/high energy frames.
17. The method of claim 15 , wherein the beat feature includes one of an amplitude of peaks in a beat histogram, a period of peaks in the beat histogram, or a ratio between a peak and a sum of all peaks in the beat histogram.
18. The method of claim 15 , wherein the pitch feature includes one of an amplitude of prominent peaks in a pitch histogram, or a period of peaks in the pitch histogram, where the pitch histogram is on a full semitone scale or an octave independent scale.
19. The method of claim 15 , wherein the semantic audio signature data includes at least one of a temporal feature, a spectral feature, a harmonic feature, or a rhythmic feature.
20. The method of claim 15 , wherein the semantic audio signature data is generated by transforming an audio signal of the media from a time domain to a frequency domain.