Automatic vocal segments detection in popular music
Publication
, Conference
Song, L; Li, M; Yan, Y
Published in: Proceedings 9th International Conference on Computational Intelligence and Security Cis 2013
December 1, 2013
We propose a technique for the automatic vocal segments detection in an acoustical polyphonic music signal. We use a combination of several characteristics specific to singing voice as the feature and employ a Gaussian Mixture Model (GMM) classifier for vocal and non-vocal classification. We have employed a pre-processing of spectral whitening and archived a performance of 81.3% over the RWC popular music dataset. © 2013 IEEE.
Duke Scholars
Published In
Proceedings 9th International Conference on Computational Intelligence and Security Cis 2013
DOI
Publication Date
December 1, 2013
Start / End Page
349 / 352
Citation
APA
Chicago
ICMJE
MLA
NLM
Song, L., Li, M., & Yan, Y. (2013). Automatic vocal segments detection in popular music. In Proceedings 9th International Conference on Computational Intelligence and Security Cis 2013 (pp. 349–352). https://doi.org/10.1109/CIS.2013.80
Song, L., M. Li, and Y. Yan. “Automatic vocal segments detection in popular music.” In Proceedings 9th International Conference on Computational Intelligence and Security Cis 2013, 349–52, 2013. https://doi.org/10.1109/CIS.2013.80.
Song L, Li M, Yan Y. Automatic vocal segments detection in popular music. In: Proceedings 9th International Conference on Computational Intelligence and Security Cis 2013. 2013. p. 349–52.
Song, L., et al. “Automatic vocal segments detection in popular music.” Proceedings 9th International Conference on Computational Intelligence and Security Cis 2013, 2013, pp. 349–52. Scopus, doi:10.1109/CIS.2013.80.
Song L, Li M, Yan Y. Automatic vocal segments detection in popular music. Proceedings 9th International Conference on Computational Intelligence and Security Cis 2013. 2013. p. 349–352.
Published In
Proceedings 9th International Conference on Computational Intelligence and Security Cis 2013
DOI
Publication Date
December 1, 2013
Start / End Page
349 / 352