Skip to Main content Skip to Navigation
Conference papers

Exploiting Semantic Content for Singing Voice Detection

Abstract : In this paper we propose a method for singing voice detection in popular music recordings. The method is based on statistical learning of spectral features extracted from the audio tracks. In our method we use Mel Frequency Cepstrum Coefficients (MFCC) to train two Gaussian Mixture Models (GMM). Special attention is brought to our novel approach for smoothing the errors produced by the automatic classification by exploiting semantic content from the songs, which will significantly boost the overall performance of the system.
Complete list of metadata

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/hal-00759923
Contributor : Jean-Luc Rouas <>
Submitted on : Monday, December 3, 2012 - 10:52:48 AM
Last modification on : Monday, March 16, 2020 - 10:58:02 AM
Long-term archiving on: : Monday, March 4, 2013 - 3:45:55 AM

File

2012_Ioannidis.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00759923, version 1

Collections

Citation

Leonidas Ioannidis, Jean-Luc Rouas. Exploiting Semantic Content for Singing Voice Detection. Sixth IEEE International Conference on Semantic Computing (IEEE ICSC2012), Sep 2012, Parlemo, Italy. ⟨hal-00759923⟩

Share

Metrics

Record views

195

Files downloads

411