Not Logged In

Unsupervised Classification of Sound for Multimedia Indexing

Full Text: mdm00-05.pdf PDF

Segmenting audio streams in a signifi cant manner and clustering sound segments objectively, is a signi ficant challenge due to the nature of audio data. This paper presents some preliminary work on clustering sound segments based on frequency and harmonic characteristics. New metrics for comparing the similarity of sound segments are also devised.

Citation

B. Matichuk, O. Zaiane. "Unsupervised Classification of Sound for Multimedia Indexing". International ACM SIGKDD Workshop on Multimedia Data Mining, pp 31-36, August 2000.

Keywords: Multimedia Data Mining, Sound Processing, Classi fication, Clustering, Similarity comparison
Category: In Workshop

BibTeX

@misc{Matichuk+Zaiane:MDM/KDD00,
  author = {Bruce Matichuk and Osmar R. Zaiane},
  title = {Unsupervised Classification of Sound for Multimedia Indexing},
  Pages = {31-36},
  booktitle = {International ACM SIGKDD Workshop on Multimedia Data Mining},
  year = 2000,
}

Last Updated: February 05, 2020
Submitted by Sabina P

University of Alberta Logo AICML Logo