diff --git a/cover_song_simplified.py b/cover_song_simplified.py new file mode 100644 index 0000000..8168681 --- /dev/null +++ b/cover_song_simplified.py @@ -0,0 +1,81 @@ +## tutorial from: https://essentia.upf.edu/essentia_python_examples.html +##In this tutorial, we use HPCP, ChromaCrossSimilarity and CoverSongSimilarity algorithms from essentia. + +import essentia.standard as estd +from essentia.pytools.spectral import hpcpgram + +yesterday_original = 'audio/Yesterday (Remastered 2009).mp3' +yesterday_cover_01 = 'audio/Yesterday - The Beatles - Connie Talbot (Cover).mp3' +yesterday_cover_02 = 'audio/The Beatles - Yesterday Saxophone Cover Alexandra Ilieva Thomann.mp3' +different_song = 'audio/Bella Poarch - Build a Btch (Official Music Video).mp3' + +# query cover song +original_song = estd.MonoLoader(filename=yesterday_original, sampleRate=32000)() +true_cover_01 = estd.MonoLoader(filename=yesterday_cover_01, sampleRate=32000)() +true_cover_02 = estd.MonoLoader(filename=yesterday_cover_02, sampleRate=32000)() + +# wrong match +false_cover_1 = estd.MonoLoader(filename=different_song, sampleRate=32000)() + +## Now let’s compute Harmonic Pitch Class Profile (HPCP) chroma features of these audio signals. +query_hpcp = hpcpgram(original_song, sampleRate=32000) +true_cover_hpcp_1 = hpcpgram(true_cover_01, sampleRate=32000) +true_cover_hpcp_2 = hpcpgram(true_cover_02, sampleRate=32000) +false_cover_hpcp = hpcpgram(false_cover_1, sampleRate=32000) + +## Next steps are done using the essentia ChromaCrossSimilarity function, +## +## Stacking input features +## +## Key invariance using Optimal Transposition Index (OTI) [3]. +## +## Compute binary chroma cross similarity using cross recurrent plot as described in [1] or using OTI-based chroma binary method as detailed in [3] + +crp = estd.ChromaCrossSimilarity(frameStackSize=9, + frameStackStride=1, + binarizePercentile=0.095, + oti=True) + +true_pair_crp_1 = crp(query_hpcp, true_cover_hpcp_1) +true_pair_crp_2 = crp(query_hpcp, true_cover_hpcp_2) + +## Compute binary chroma cross similarity using cross recurrent plot of the non-cover pairs + +false_pair_crp = crp(query_hpcp, false_cover_hpcp) + +## Alternatively, you can also use the OTI-based binary similarity method as explained in [2] to compute the cross similarity of two given chroma features. + +csm = estd.ChromaCrossSimilarity(frameStackSize=9, + frameStackStride=1, + binarizePercentile=0.095, + oti=True, + otiBinary=True) + +oti_csm = csm(query_hpcp, false_cover_hpcp) + + +## Finally, we compute an asymmetric cover song similarity measure from the pre-computed binary cross simialrity matrix of cover/non-cover pairs using various contraints of smith-waterman sequence alignment algorithm (eg. serra09 or chen17). +## +## Computing cover song similarity distance between ‘Yesterday - accapella cover’ and ‘Yesterday - The Beatles’ + +score_matrix, distance = estd.CoverSongSimilarity(disOnset=0.5, + disExtension=0.5, + alignmentType='serra09', + distanceType='asymmetric')(true_pair_crp_1) +print('Cover song similarity distance: %s' % distance) + +## other similar + +score_matrix, distance = estd.CoverSongSimilarity(disOnset=0.5, + disExtension=0.5, + alignmentType='serra09', + distanceType='asymmetric')(true_pair_crp_2) +print('Cover song similarity distance: %s' % distance) + +## Computing cover song similarity distance between Yesterday - accapella cover and Come Together cover - The Aerosmith. + +score_matrix, distance = estd.CoverSongSimilarity(disOnset=0.5, + disExtension=0.5, + alignmentType='serra09', + distanceType='asymmetric')(false_pair_crp) +print('Cover song similarity distance: %s' % distance)