Method and system for retrieving and sequencing music by rhythmic similarity

• US 20030205124A1
• Filed: 04/01/2003
• Published: 11/06/2003
• Est. Priority Date: 05/01/2002
• Status: Abandoned Application

• Current Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: Cooper, Matthew L., Foote, Jonathan T.
• Application Number:
  US10/405,192
• Publication Number:
  US 20030205124A1
• Time in Patent Office: Days
• US Class Current: 84/608
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G10G 1/00 Means for the representation of music
• CPC Class Codes: G10H 1/40 Rhythm
• CPC Class Codes: G10H 2210/041 based on mfcc [mel -frequency spectral coefficients]
• CPC Class Codes: G10H 2210/071 for rhythm pattern analysis or rhythm style recognition rhythm pattern per se G10H2210/341
• CPC Class Codes: G10H 2240/056 MIDI or other note-oriented file format
• CPC Class Codes: G10H 2240/061 MP3, i.e. MPEG-1 or MPEG-2 Audio Layer III, lossy audio compression
• CPC Class Codes: G10H 2250/235 Fourier transform; Discrete Fourier Transform [DFT]; Fast Fourier Transform [FFT]
• CPC Class Codes: G10H 2250/281 Hamming window

Abstract

A method for measuring the similarity between the beat spectra of two or more audio works. A distance formula is used to measure the similarity by rhythm and tempo between shortened beat spectra B₁(L) and B₂(L). The result is a vector which measures the similarity of rhythm and tempo. A distance formula is used to measure the rhythmic similarity between the scaled beat spectra B₁(L) and B₂(L). The result is a measure of rhythmically similar music regardless of the tempo. The method can be used in a wide variety of applications, including concatenating music with similar tempos, automatic music sequencing, classification of music into genres, search for music with similar rhythmic structures, search for music with similar rhythmic and tempo structures, and ranking music according to a similarity measure.

Claims

1. A method for comparing at least two auditory works, comprising the steps of:

receiving a first auditory work and a second auditory work;

determining a first feature vector representative of said first auditory work;

determining a second feature vector representative of said second auditory work;

calculating a first beat spectrum from said first feature vector;

calculating a second beat spectrum from said second feature vector; and

,

measuring a similarity value of said first beat spectrum and said second beat spectrum.

2. The method of claim 1, further comprising the steps of:

windowing said first auditory work into a first plurality of windows;

windowing said second auditory work into a second plurality of windows;

wherein said step of determining said first feature vector includes the step of;

determining a first plurality of feature vectors representative of said first plurality of windows; and

wherein said step of determining said second feature vector includes the step of;

determining a second plurality of feature vectors representative of said second plurality of windows.

3. The method of claim 2, wherein said step of calculating a first beat spectrum includes the steps of:

determining a first similarity between feature vectors of said first plurality of feature vectors; and

,

calculating said first beat spectrum from said first similarity; and

wherein the step of calculating a second beat spectrum includes the steps of;

determining a second similarity between feature vectors of said second plurality of feature vectors; and

,

calculating said second beat spectrum from said second similarity.

4. The method of claim 1, wherein said first beat spectrum is a function of a lag time, and

wherein said second beat spectrum is a function of said lag time.

5. The method of claim 4, wherein said first beat spectrum is truncated based upon said lag time and said second beat spectrum is truncated based upon said lag time.

6. The method of claim 1, wherein said step of measuring includes measuring a Euclidean distance between said first beat spectrum and said second beat spectrum.

7. The method of claim 1, wherein said step of measuring includes measuring a dot product between said first beat spectrum and said second beat spectrum.

8. The method of claim 1, wherein said step of measuring includes measuring a normalized dot product between said first beat spectrum and said second beat spectrum.

9. The method of claim 1, wherein said step of measuring includes the steps of:

computing a Fourier Transform for said first beat spectrum and said second beat spectrum; and

measuring a Euclidean distance between said Fourier Transform of said first beat spectrum and said second beat spectrum.

10. The method of claim 1, wherein said step of measuring includes the steps of:

computing a Fourier Transform for said first beat spectrum and said second beat spectrum; and

measuring a dot product between said Fourier Transformed first beat spectrum and said second beat spectrum.

11. The method of claim 1, wherein said step of measuring includes the steps of:

computing a Fourier Transform for said first beat spectrum and said second beat spectrum; and

measuring a normalized dot product for said Fourier Transformed first beat spectrum and said second beat spectrum.

12. The method of claim 1, wherein said step of measuring the similarity includes measuring the similarity by rhythm and tempo.

13. The method of claim 1, wherein said step of measuring the similarity includes measuring the similarity by rhythm.

14. The method of claim 1, wherein said step of measuring the similarity includes measuring the similarity by tempo.

15. A method for determining a beat spectrum for an auditory work, comprising the steps of:

receiving an auditory work;

windowing said auditory work into a plurality of windows;

determining a feature vector representative of each of said windows;

computing a similarity matrix for a combination of each said feature vector; and

generating a beat spectrum from said similarity measure.

16. The method of claim 15, wherein said step of computing a similarity matrix is computed based upon a Euclidean distance between said combination of feature vectors.

17. The method of claim 15, wherein said step of computing a similarity matrix is computed based upon a dot product of said combination of feature vectors.

18. The method of claim 15, wherein said step of computing a similarity matrix is computed based upon a dot product of said combination of feature vectors.

19. The method of claim 15, wherein said beat spectrum is a measurement of said similarity matrix as a function of a lag of said auditory work.

20. The method of claim 15 wherein said beat spectrum is utilized for determining a rhythmic variation of said auditory work over time.

21. The method of claim 15, wherein said beat spectrum indicates how a tempo of said auditory work varies over time.