Loading...

Birth-death frequencies variance of sinusoidal model a new feature for audio classification

Ghaemmaghami, S ; Sharif University of Technology | 2008

498 Viewed
  1. Type of Document: Article
  2. Publisher: 2008
  3. Abstract:
  4. In this paper, a new feature set for audio classification is presented and evaluated based on sinusoidal modeling of audio signals. Variance of the birth-death frequencies in sinusoidal model of signal, as a measure of harmony, is used and compared to typical features as the input into an audio classifier. The performance of this sinusoidal model feature is evaluated through classification of audio to speech and music using both the GMM and the SVM classifiers. Classification results show that the proposed feature is quite successful in speech/music classification. Experimental comparisons with popular features for audio classification, such as HZCRR and LSTER, are presented and discussed. By using a set of three features, we achieved 96.83% accuracy, in one-sec segment based audio classification
  5. Keywords:
  6. Classifiers ; Learning systems ; Signal processing ; Audio classification ; Audio classifications ; Audio signals ; Classification results ; Experimental comparisons ; Feature sets ; Segment based ; Sinusoidal model ; Sinusoidal models ; Speech/music classifications ; Svm classifiers ; Audio acoustics
  7. Source: SIGMAP 2008 - International Conference on Signal Processing and Multimedia Applications, Porto, 26 July 2008 through 29 July 2008 ; 2008 , Pages 139-144 ; 9789898111609 (ISBN)
  8. URL: https://dblp.org/db/conf/sigmap/sigmap2008.html