Methods and apparatus to extract a pitch-independent timbre attribute from a media signal
Methods and apparatus to extract a pitch-independent timbre attribute from a media signal are disclosed. An example apparatus includes an audio characteristic extractor to determine a logarithmic spectrum of an audio signal; transform the logarithmic spectrum of the audio signal into a frequency domain to generate a transform output; determine a magnitude of the transform output; and determine a timbre attribute of the audio signal based on an inverse transform of the magnitude.
1. A non-transitory computer readable storage medium comprising instructions which, when executed cause one or more processors to at least:
access a media signal;
extract a pitch-independent timbre spectrum of the accessed media signal; and
classify the accessed media signal based on data corresponding to the pitch-independent timbre spectrum, wherein the classification corresponds to at least one of an instrument or a genre.
2. The non-transitory computer readable storage medium of claim 1 , wherein the media signal comprises an audio signal.
3. The non-transitory computer readable storage medium of claim 1 , wherein the media signal comprises an audio component of a video signal.
4. The non-transitory computer readable storage medium of claim 3 , wherein the instructions further comprise instructions that cause the one or more processors to extract the media signal from the video signal.
5. The non-transitory computer readable storage medium of claim 1 , wherein extracting a pitch-independent timbre of the accessed media signal comprises determining a logarithmic spectrum of the media signal and transforming the logarithmic spectrum of the media signal into a frequency domain to generate a transform output.
6. The non-transitory computer readable storage medium of claim 5 , wherein determining the logarithmic spectrum of the media signal comprises using a constant Q transform.
7. The non-transitory computer readable storage medium of claim 5 , wherein extracting a pitch-independent timbre of the accessed media signal comprises determining a magnitude of the transform output and a timbre attribute of the media signal based on an inverse transform of the magnitude.
8. The non-transitory computer readable storage medium of claim 7 , wherein determining the transform of the logarithmic spectrum is based on a Fourier transform and determining the inverse transform is based on using an inverse Fourier transform.
9. The non-transitory computer readable storage medium of claim 7 , wherein determining a timbre-independent pitch attribute of the media signal is based on an inverse transform of a complex argument of the transform of the logarithmic spectrum.
10. The non-transitory computer readable storage medium of claim 1 , wherein the instructions further comprise instructions that cause the one or more processors to identify a media source of the media signal based on the classification.
11. The non-transitory computer readable storage medium of claim 1 , wherein the instructions further comprise instructions that cause the one or more processors to compare the pitch-independent timbre spectrum of the media signal to one or more reference pitch-independent timbre spectrums, and wherein classifying the media signal is based on matching one or more reference pitch-independent timbre spectrums to the extracted pitch-independent timbre spectrum.
12. The non-transitory computer readable storage medium of claim 1 , wherein the instructions further comprise instructions that cause the one or more processors to compare the pitch-independent timbre spectrum of the media signal to one or more reference pitch-independent timbre spectrums, and based on determining that the extracted pitch-independent timbre spectrum does not match the one or more reference pitch-independent timbre spectrums, prompt for additional information corresponding to the media signal.
13. The non-transitory computer readable storage medium of claim 1 , wherein the instructions further comprise instructions that cause the one or more processors to determine a device setting adjustment based on the classification.
14. A method comprising:
accessing, by one or more processors, a media signal;
extracting, by the one or more processors, a pitch-independent timbre spectrum of the accessed media signal; and
classifying, by the one or more processors, the accessed media signal based on data corresponding to the pitch-independent timbre spectrum, wherein the classification corresponds to at least one of an instrument or a genre.
15. The method of claim 14 , wherein the media signal comprises an audio signal.
16. The method of claim 14 , wherein the media signal comprises an audio component of a video signal.
17. The method of claim 16 , wherein the method further comprises extracting the media signal from the video signal.
18. The method of claim 14 , wherein extracting a pitch-independent timbre of the accessed media signal comprises determining a logarithmic spectrum of the media signal and transforming the logarithmic spectrum of the media signal into a frequency domain to generate a transform output.
19. The method of claim 14 , wherein the method further comprises identifying a media source of the media signal based on the classification.
20. An apparatus comprising:
an interface to receive a media signal; and
one or more processors to at least:
access the media signal;
extract a pitch-independent timbre spectrum of the accessed media signal; and
classify the accessed media signal based on data corresponding to the pitch-independent timbre spectrum, wherein the classification corresponds to at least one of an instrument or a genre.