Audio signal analysis
View Patent ↗A server system 500 is provided for receiving video clips having an associated audio/musical track for processing at the server system. The system comprises a first beat tracking module for generating a first beat time sequence from the audio signal using an estimation of the signal's tempo and chroma accent information. A ceiling and floor function is applied to the tempo estimation to provide integer versions which are subsequently applied separately to a further accent signal derived from a lower-frequency sub-band of the audio signal to generate second and third beat time sequences. A selection module then compares each of the beat time sequences with the further accent signal to identify a best match.
1. Apparatus, the apparatus having at least one processor and at least one memory having computer-readable code stored thereon which when executed controls the at least one processor:
to generate a first accent signal (a 1 ) representing musical accents in an audio signal by extracting chroma accent features based on fundamental frequency (f 0 ) salience analysis;
to generate a second, different, accent signal (a 2 ) representing musical accents in the audio signal by using a predetermined sub-band of the audio signal's bandwidth;
to estimate a first beat time sequence (b i ) from the first accent signal;
to estimate a second beat time sequence (b 2 ) from the second accent signal; and
to identify which one of the first and second beat time sequences (b i ) (b 2 ) corresponds most closely with peaks in one or both of the accent signal(s).
2. Apparatus according to claim 1 , wherein the computer-readable code when executed controls the at least one processor to generate using the first accent signal (a 1 ) an estimated tempo (BPM est ) of the audio signal.
3. Apparatus according to claim 2 , wherein the computer-readable code when executed controls the at least one processor to generate the first beat time sequence using the first accent signal (a 1 ) and the estimated tempo (BPM est ).
4. Apparatus according to claim 2 , wherein the computer-readable code when executed controls the at least one processor to obtain an integer representation of the estimated tempo (BPM est ) and generate the second beat time sequence (b 2 ) using the second accent signal (a 2 ) and said integer representation.
5. Apparatus according to claim 4 , wherein the computer-readable code when executed controls the at least one processor to calculate the integer representation of the estimated tempo (BPM est ) using either a rounded tempo estimate function (round(BPM est )), a ceiling tempo estimate function (ceil(BPM est )) or a floor tempo estimate function (floor(BPM est )).
6. Apparatus according to claim 2 , wherein the computer-readable code when executed controls the at least one processor to perform a ceiling and floor function on the estimated tempo (BPM est ) to generate respectively a ceiling tempo estimate (ceil(BPM est ) and a floor tempo estimate (floor(BPM est )), to generate the second and a third beat time sequence (b 2 ) (b 3 ) using the second accent signal (a 2 ) and different ones of the ceiling and floor tempo estimates, and to identify which one of the first, second and third beat time sequences corresponds most closely with peaks in one or both of the accent signal(s).
7. Apparatus according to claim 6 , wherein the computer-readable code when executed controls the at least one processor to generate, for each of the ceiling and floor tempo estimates, an initial beat time sequence (b t ) using said estimate, said initial beat time sequence then being compared with a reference beat time sequence (b i ) for generating the second and third beat time sequences using a predetermined similarity algorithm.
8. Apparatus according to claim 7 , wherein the computer-readable code when executed controls the at least one processor to compare the initial beat time sequence (b t ) and the reference beat time sequence (b i ) over a range of offset positions to identify a best match within the range, the generated second/third beat time sequence comprising the offset version of the reference beat time sequence (b i ) which resulted in the best match.
9. Apparatus according to claim 7 , wherein the reference beat time sequence (b) has a constant beat interval.
10. Apparatus according to claim 9 wherein the computer-readable code when executed controls the at least one processor to generate the reference beat time sequence (b i ) as t=0, 1/(X/60), 2/(X/60) . . . n/(X/60) where X is the integer representation of the estimated tempo and n is an integer.
11. Apparatus according to claim 8 , wherein the computer-readable code when executed controls the at least one processor to use a range of offset positions in the algorithm of about 0 and 1.1/(X/60) where X is the integer representation of the estimated tempo.
12. Apparatus according to claim 8 , wherein the computer-readable code when executed controls the at least one processor to use offset positions for comparison in the algorithm having steps of 0.1/(BPM est /60).
13. Apparatus according to claim 1 , wherein the computer-readable code when executed controls the at least one processor to identify which one of the beat time sequences corresponds most closely with peaks in the second accent signal.
14. Apparatus according to claim 1 , wherein the computer-readable code when executed controls the at least one processor to calculate, for each of the beat time sequences, the average or mean value of the or each accent signal occurring at or around beat times in the sequence, and to select the beat time sequence which results in the greatest mean value.
15. A method comprising:
generating a first accent signal (a 1 ) representing musical accents as a function of time in an audio signal by extracting chroma accent features based on fundamental frequency (f 0 ) salience analysis;
generating a second, different, accent signal (a 2 ) representing low frequency musical accents in the audio signal by using a predetermined sub-band of the audio signal's bandwidth;
estimating a first beat time sequence (b 1 ) from the first accent signal;
estimating a second beat time sequence (b 2 ) from the second accent signal; and
identifying which one of the first and second beat time sequences (b 1 ) (b 2 ) corresponds most closely with peaks in one or both of the accent signal(s).
16. The method according to claim 15 , further comprising:
generating using the first accent signal (a 1 ) an estimated tempo (BPM est ) of the audio signal.
17. The method according to claim 15 , further comprising:
identifying which one of the beat time sequences corresponds most closely with peaks in the second accent signal.
18. A computer program product comprising at least one computer readable non-transitory medium having program code stored thereon, the program code, when executed by an apparatus, causing the apparatus at least to:
generate a first accent signal (a 1 ) representing musical accents as a function of time in an audio signal by extracting chroma accent features based on fundamental frequency (f 0 ) salience analysis;
generate a second, different, accent signal (a 2 ) representing low frequency musical accents in the audio signal by using a predetermined sub-band of the audio signal's bandwidth;
estimate a first beat time sequence (b 1 ) from the first accent signal;
estimate a second beat time sequence (b 2 ) from the second accent signal; and
identify which one of the first and second beat time sequences (b 1 ) (b 2 ) corresponds most closely with peaks in one or both of the accent signal(s).
19. The computer program product according to claim 18 , wherein the program code further causing the apparatus at least to:
generate using the first accent signal (a 1 ) an estimated tempo (BPM est ) of the audio signal.
20. The computer program product according to claim 18 , wherein the program code further causing the apparatus at least to:
identifying which one of the beat time sequences corresponds most closely with peaks in the second accent signal.