Systems and methods for automated music rearrangement
A method and apparatus of a device that builds a target using a plurality of processing units is described. In an exemplary embodiment, the device receives an input audio track having a first duration, the input audio track having a plurality of points. The device further generates a transition matrix of the input audio track, wherein the transition matrix indicates a similarity metric between different pairs of the plurality of points. In addition, the device determines a set of jump points using the different pairs of the plurality of points. The device additionally generates the rearranged audio track using the set of jump points, wherein the rearranged audio track has second duration and the second duration is different than the first duration.
1. A non-transitory machine-readable medium having executable instructions to cause one or more processing units to perform a method to rearrange an input audio track into a rearranged audio track, the method comprising:
receiving an input audio track having a first duration, the input audio track having a plurality of points;
generating a transition matrix of the input audio track, wherein the transition matrix indicates a similarity metric between different pairs of the plurality of points;
determining a set of jump points using the different pairs of the plurality of points; and
generating the rearranged audio track using the set of jump points, wherein the rearranged audio track has a second duration, the second duration is different than the first duration, and the rearranged audio track is a set of non-contiguous audio subsets of the input audio track that are coupled via the set of jump points.
2. The non-transitory machine readable medium of claim 1 , wherein a jump point is a jump from one point in the input audio track to another point in the input audio track.
3. The non-transitory machine-readable medium of claim 1 , wherein a point in the plurality of points is selected from the group consisting of a beat, a bar, a segment, and a section.
4. The non-transitory machine readable medium of claim 1 , further comprising:
computing the transition matrix.
5. The non-transitory machine readable medium of claim 4 , wherein computing the transition matrix comprises:
decomposing the input audio track into a percussive track and a harmonic track; and
chunking the percussive track and a harmonic track into input features via the computation of a perceptual Mel power spectrograms and perceptual CQT power spectrograms that captures different audio.
6. The non-transitory machine readable medium of claim 4 , wherein the input features include transients, timber, and pitches.
7. The non-transitory machine readable medium of claim 4 , further comprising:
computing the transition matrix using the input features using machine learning.
8. The non-transitory machine readable medium of claim 1 , further comprising:
determining a starting point for the rearranged audio track.
9. The non-transitory machine readable medium of claim 7 , wherein the starting point is after a starting point of the input audio track.
10. The non-transitory machine readable medium of claim 1 , further comprising:
determining an ending point for the rearranged audio track.
11. The non-transitory machine readable medium of claim 1 , further comprising:
generating a set of video cues for the rearranged audio track.
12. A method to rearrange an input audio track into a rearranged audio track, the method comprising:
receiving an input audio track having a first duration, the input audio track having a plurality of points;
generating a transition matrix of the input audio track, wherein the transition matrix indicates a similarity metric between different pairs of the plurality of points;
determining a set of jump points using the different pairs of the plurality of points; and
generating the rearranged audio track using the set of jump points, wherein the rearranged audio track has a second duration, the second duration is different than the first duration, and the rearranged audio track is a set of non-contiguous audio subsets of the input audio track that are coupled via the set of jump points.
13. The method of claim 12 , wherein a jump point is a jump from one point in the input audio track to another point in the input audio track.
14. The method of claim 12 , wherein a point in the plurality of points is selected from the group consisting of a beat, a bar, a segment, and a section.
15. The method of claim 12 , further comprising:
computing the transition matrix.
16. The method of claim 15 , wherein computing the transition matrix comprises:
decomposing the input audio track into a percussive track and a harmonic track; and
chunking the percussive track and a harmonic track into input features via the computation of a perceptual Mel power spectrograms and perceptual CQT power spectrograms that captures different audio.
17. The method of claim 16 , wherein the features include transients, timber, and pitches.
18. The method of claim 16 , further comprising:
computing the transition matrix using the input features using machine learning.
19. The method of claim 12 , further comprising:
determining a starting point for the rearranged audio track.
20. The method of claim 19 , wherein the starting point is after a starting point of the input audio track.
21. A device that rearranges an input audio track into a rearranged audio track, the device comprising:
at least one processing unit;
memory coupled to the at least one processing unit; and
a process executed from the memory by the processing unit that causes the at least one processing unit to receive an input audio track having a first duration, the input audio track having a plurality of points, generate a transition matrix of the input audio track, wherein the transition matrix indicates a similarity metric between different pairs of the plurality of points, determine a set of jump points using the different pairs of the plurality of points, and generate the rearranged audio track using the set of jump points, wherein the rearranged audio track has second duration, the a second duration is different than the first duration, and the rearranged audio track is a set of non-contiguous audio subsets of the input audio track that are coupled via the set of jump points.