Methods and apparatus to extract a pitch-independent timbre attribute from a media signal

Patent metadata

Field	Value
Publication number	US-11749244-B2
Application number	US-202117157780-A
Country	US
Kind code	B2
Filing date	Jan 25, 2021
Priority date	Mar 13, 2018
Publication date	Sep 5, 2023
Grant date	Sep 5, 2023

Abstract

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.

First claim

What is claimed is:

1. An apparatus comprising:
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.

2. The apparatus of claim 1 , wherein the audio signal is part of a media signal.

3. The apparatus of claim 1 , wherein the audio signal is an audio component of a video signal, further including an audio extractor to extract the audio signal from the video signal.

4. The apparatus of claim 1 , wherein the audio characteristic extractor is to determine the logarithmic spectrum of the audio signal using a constant Q transform.

5. The apparatus of claim 1 , wherein the audio characteristic extractor is to determine the transform of the logarithmic spectrum using a Fourier transform and determine the inverse transform using an inverse Fourier transform.

6. The apparatus of claim 1 , wherein the audio characteristic extractor is to determine a timbre-independent pitch attribute of the audio signal based on an inverse transform of a complex argument of the transform of the logarithmic spectrum.

7. The apparatus of claim 1 , further including an interface to:
transmit the timbre attribute to a processing device; and
in response to transmitting the timbre attribute to the processing device, receive at least one of a classification of the audio signal or an identifier corresponding to a media signal corresponding to the audio signal from the processing device.

8. The apparatus of claim 7 , wherein the interface is to transmit the at least one of the classification of the audio signal or the identifier corresponding to the media signal to a user interface.

9. The apparatus of claim 1 , further including a microphone to receive the audio signal via ambient audio.

10. The apparatus of claim 1 , wherein the audio signal corresponds to a media signal to be output by a media output device.

11. The apparatus of claim 1 , further including an interface to receive the audio signal from a microphone.

12. A non-transitory computer readable storage medium comprising instructions which, when executed, cause a one or more processors to at least:
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.

13. The computer readable storage medium of claim 12 , wherein the audio signal is part of a media signal.

14. The computer readable storage medium of claim 12 , wherein the audio signal is a an audio component of a video signal, wherein the instructions when executed cause the one or more processors to extract the audio signal from the video signal.

15. The computer readable storage medium of claim 12 , wherein the instructions when executed cause the one or more processors to determine the logarithmic spectrum of the audio signal using a constant Q transform.

16. The computer readable storage medium of claim 12 , wherein the instructions when executed cause the one or more processors to determine the transform of the logarithmic spectrum using a Fourier transform and determine the inverse transform using an inverse Fourier transform.

17. The computer readable storage medium of claim 12 , wherein the instructions when executed cause the one or more processors to determine a timbre-independent pitch attribute of the audio signal based on an inverse transform of a complex argument of the transform of the logarithmic spectrum.

18. The computer readable storage medium of claim 12 , wherein the instructions when executed cause the one or more processors to:
transmit the timbre attribute to a processing device; and
in response to transmitting the timbre attribute to the processing device, receive at least one of a classification of the audio signal or an identifier corresponding to a media signal corresponding to the audio signal from the processing device.

19. The computer readable storage medium of claim 18 , wherein the instructions when executed cause the one or more processors to transmit the at least one of the classification of the audio signal or the identifier corresponding to the media signal to a user interface.

20. An apparatus comprising:
means for determining a timbre attribute of an audio signal, the means for determining to:
determine a logarithmic spectrum of the 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 the timbre attribute of the audio signal based on an inverse transform of the magnitude.

Assignees

• Nielsen Co Us Llc
• The Nielson Company Us Llc

Inventors

• Rafii Zafar

Classifications

• G10H3/125 Primary

  Extracting or recognising the pitch or fundamental frequency of the picked up signal · CPC title

• G10H1/06 Primary

  Circuits for establishing the harmonic content of tones {, or other arrangements for changing the tone colour} · CPC title

• G10H2210/056

  for extraction or identification of individual instrumental parts, e.g. melody, chords, bass; Identification or separation of instrumental parts by their characteristic voices or timbres · CPC title

• G10H2250/221

  Cosine transform; DCT [discrete cosine transform], e.g. for use in lossy audio compression such as MP3 · CPC title

• G10H2250/235

  Fourier transform; Discrete Fourier Transform [DFT]; Fast Fourier Transform [FFT] · CPC title