Systems and methods for musical tempo detection

Patent metadata

Field	Value
Publication number	US-11928001-B2
Application number	US-201816476452-A
Country	US
Kind code	B2
Filing date	Jan 5, 2018
Priority date	Jan 9, 2017
Publication date	Mar 12, 2024
Grant date	Mar 12, 2024

Abstract

Systems and methods for musical tempo detection are provided. The method includes detecting peaks and their locations in a waveform of a digital audio track, and dividing the track into first measures with a first-measure length based on a first estimated tempo. The method includes determining distances between a beginning of the first measures and each peak location, and determining a first number of peaks having the same distance from the beginning of the first measures. The method includes dividing the track into second measures with a second-measure length based on a second estimated tempo; determining distances between a beginning of the second measures and each peak location; and determining a second number of peaks having the same distance from the beginning of each of the second measures. The method includes estimating an accurate tempo by comparing the first number of peaks and the second number of peaks.

First claim

What is claimed is:

1. A method for determining an accurate measure length and a corresponding musical tempo of a digital audio track, the method comprising:
detecting a plurality of peaks and peak locations in a waveform of the digital audio track;
estimating a first tempo of said digital audio track;
dividing the digital audio track into a first plurality of measures, wherein the length of each of the first plurality of measures is based on the first tempo;
determining the distances between a beginning of each of the first plurality of measures and each peak location within said first plurality of measures;
determining a first number of peaks having the same distance from the beginning of each of the first plurality of measures containing each peak location;
estimating a second tempo of said digital audio track;
dividing the digital audio track into a second plurality of measures, wherein the length of each of the second plurality of measures is based on the second tempo;
determining the distances between a beginning of each of the second plurality of measures and each peak location within said second plurality of measures;
determining a second number of peaks having the same distance from the beginning of each of the second plurality of measures containing each peak location; and
determining whether the accurate measure length corresponds to the first tempo or corresponds to the second tempo by comparing the first number of peaks and the second number of peaks, wherein the accurate measure length corresponds to the first tempo when the first number of peaks is greater than the second number of peaks.

2. The method of claim 1 , further comprising generating the waveform of the digital audio track by passing the digital audio track through at least one bandpass filter.

3. The method of claim 1 , further comprising generating the waveform of the digital audio track by downsampling the digital audio track.

4. The method of claim 1 , wherein estimating the accurate measure length is further based on the sound pressure level associated with each peak location of the plurality of peak locations.

5. The method of claim 1 , wherein estimating the accurate measure length is further based on one or more frequencies of sound energy associated with each peak location of the plurality of peak locations.

6. The method of claim 1 , further comprising determining downbeat locations to be the peak locations contained within the first plurality of measures and having the greatest number of peaks at the peak locations relative to other peak locations.

7. The method of claim 1 , further comprising determining downbeat locations based on the number of peaks at peak locations contained within the first plurality of measures and the sound pressure level of the peaks at the peak locations.

8. The method of claim 1 , further comprising determining downbeat locations based on the number of peaks at peak locations contained within the first plurality of measures and one or more frequencies of sound energy associated with the peaks at the peak locations.

9. A system comprising a processor and a non-transitory computer-readable storage medium storing instruction that, when executed by the processor, cause the processor to perform a method for determining an accurate measure length and musical tempo, the method comprising:
detecting a plurality of peaks and peak locations in a waveform of the digital audio track;
estimating a first tempo of said digital audio track;
dividing the digital audio track into a first plurality of measures, wherein the length of each of the first plurality of measures is based on the first tempo;
determining the distances between a beginning of each of the first plurality of measures and each peak location within said first plurality of measures;
determining a first number of peaks having the same distance from the beginning of each of the first plurality of measures containing each peak location;
estimating a second tempo of said digital audio track;
dividing the digital audio track into a second plurality of measures, wherein the length of each of the second plurality of measures is based on the second tempo;
determining a second number of peaks having the same distance from the beginning of each of the second plurality if measures containing each peak location; and
determining whether the accurate measure length corresponds to the first tempo or corresponds to the second tempo by comparing the first number of peaks and the second number of peaks, wherein the accurate measure length corresponds to the first tempo when the first number of peaks is greater than the second number of peaks.

10. The system of claim 9 , wherein the method further comprises generating the waveform of the digital audio track by passing the digital audio track through at least one bandpass filter.

11. The system of claim 9 , wherein the method further comprises generating the waveform of the digital audio track by downsampling the digital audio track.

12. The system of claim 9 , wherein estimating the accurate measure length is further based on the sound pressure level associated with each peak location of the plurality of peak locations.

13. The system of claim 9 , wherein estimating the accurate measure length is further based on one or more frequencies of sound energy associated with each peak location of the plurality of peak locations.

14. The system of claim 9 , wherein the method further comprises determining downbeat locations to be the peak locations contained within the first plurality of measures and having the greatest number of peaks at the peak locations relative to other peak locations.

15. The system of claim 9 , wherein the method further comprises determining downbeat locations based on the number of peaks at peak locations contained within the first plurality of measures and the sound pressure level of the peaks at the peak locations.

16. The system of claim 9 , wherein the method further comprises determining downbeat locations based on the number of peaks at peak locations contained within the first plurality of measures and one or more frequencies of sound energy associated with the peaks at the peak locations.

17. The system of claim 9 , wherein the system is a DJ media player.

18. The system of claim 9 , wherein a user selects the digital audio track based on a musical tempo associated with the accurate measure length.

19. A non-transitory computer-readable medium storing instructions executable by at least one processor to facilitate regulating network resources to improve data-transmission quality, according to a method for determining an accurate measure length and musical tempo, the method comprising:
detecting a plurality of peaks and peak locations in a waveform of the digital audio track;
estimating a first tempo of said digital audio track;
dividing the digital audio track into a first plurality of measures, wherein the length of each of the first plurality of measures is based on the first tempo;
determining the distances between a beginning of each of the first plurality of measures and each peak location within said first plurality of measures;
determining a first number of peaks having the same distance from the beginning of each of the first plurality of measures containing each peak location;
estimating a second tempo of said digital audio track;
dividing the digital audio track into a second plurality of measures, wherein the length of each of the second plurality of measures is based on the second t

Assignees

• Inmusic Brands Inc

Inventors

• O'Donnell John
• Roman Christopher Blane
• Heintz James Samuel
• Kaletta Manuel
• Tillmans Marcus

Classifications

• G06F16/683

  using metadata automatically derived from the content · CPC title

• G10L21/043

  by changing speed · CPC title

• G06F1/30 Primary

  Means for acting in the event of power-supply failure or interruption, e.g. power-supply fluctuations (for resetting only G06F1/24) · CPC title

• G06F3/0362

  with detection of one-dimensional [1D] translations or rotations of an operating part of the device, e.g. scroll wheels, sliders, knobs, rollers or belts · CPC title

• G06F3/044

  by capacitive means · CPC title