J. L. Whitney and C. N. Leider, “Automatic Sample Recognition in Hip-Hop Music Based on Non-Negative Matrix Factorization,” in Proc. AES Convention 134, May 2013, pp. 8851:1-19. [Online]. Available: https://aes.org/publications/elibrary-page/?id=16752
Whitney JL, Leider CN. Automatic Sample Recognition in Hip-Hop Music Based on Non-Negative Matrix Factorization. In: AES Convention 134. Audio Engineering Society; 2013.pp. 8851:1-19. Available from: https://aes.org/publications/elibrary-page/?id=16752
@inproceedings{Whitney2013_16752,
author = {Whitney, Jordan L. and Leider, Colby N.},
title = {{Automatic Sample Recognition in Hip-Hop Music Based on Non-Negative Matrix Factorization}},
booktitle = {AES Convention 134},
pages = {8851:1-19},
url = {https://aes.org/publications/elibrary-page/?id=16752},
year = {2013},
month = may,
publisher = {Audio Engineering Society},
address = {Rome Italy}
}
TY - CPAPER
TI - Automatic Sample Recognition in Hip-Hop Music Based on Non-Negative Matrix Factorization
AU - Whitney, Jordan L.
AU - Leider, Colby N.
T2 - AES Convention 134
SP - 1
EP - 19
M1 - Paper 8851
PY - 2013
DA - 2013/05/06
UR - https://aes.org/publications/elibrary-page/?id=16752
PB - Audio Engineering Society
CY - Rome Italy
LA - en
AB - We present a method for automatic detection of samples in hip-hop music. A sample is defined as a short extraction from a source audio corpus that may have been embedded into another audio mixture. A series of non-negative matrix factorizations are applied to spectrograms of hip-hop music and the source material from a master corpus. The factorizations result in matrices of base spectra and amplitude envelopes for the original and mixed audio. Each window of the mixed audio is compared to the original audio clip by examining the extracted amplitude envelopes. Several image-similarity metrics are employed to determine how closely the samples and mixed amplitude envelopes match. Preliminary testing indicates that, distinct from existing audio fingerprinting algorithms, the algorithm we describe is able to confirm instances of sampling in a hip-hop music mixture that the untrained listener is frequently unable to detect.
ER -