Loading...

Automatic Music Signal Classification Through Hierarchical Clustering

Delfani, Erfan | 2014

430 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 46516 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Ghaemmaghami, Shahrokh
  7. Abstract:
  8. The rapid increase in the size of digital multimedia data collections has resulted in wide availability of multimedia contents to the general users. Effective and efficient management of these collections is an important task that has become a focus in the research of multimedia signal processing and pattern recognition. In this thesis, we address the problem of automatic classification of music, as one of the main multimedia signals. In this context, music genres are crucial descriptors that are widely used to organize the large music collections. The two main components of automatic music genre classification systems are feature extraction and classification. While features are a compact representation of music signals, classifier relates the features to the genres. In this thesis, we design an automatic music genre classification system. Besides, based on physical and perceptual aspects of music in different genres, we propose new models for timbre, rhythm and pitch. Also, according to the nature of the music genres, we propose a supervised hierarchical clustering method forming a hierarchy of genres. The proposed method is a feature-selection based and therefore is evaluated by different feature-selection methods. Finally, the classifiers are trained in each hierarchy level and then are tested using well-known datasets. Results show the superb performance of the proposed methods compared to the state of the art methods
  9. Keywords:
  10. Hierarchical Clustering ; Signal Classification ; Music Classification ; Music Signal ; Musical Genre ; Genre Classification

 Digital Object List

 Bookmark

No TOC