Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 47891 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Sameti, Hossein
- Abstract:
- Music information reterival systems have a lot of applications in music filtering and broadcast monitoring due to the huge amount of multimedia data these days. In these systems the feature extraction method is called audio fingerprinting. Small size of fingerprints allows the systems to search efficiently in thousands or millions numbers of audio songs. The input signal is usually just a couple of seconds long and degraded in several ways. The goal is to design a system which is robust to signal degradations and efficient to search. In this thesis one of the basic systems is reviewed and improved in several ways. This system uses spectrogram of signals to extract features and build an indexing structure to search. Robustness to signal degradation and efficient search strategy are the main aspects of consideration on improving in this thesis. In order to bulid a more robust feature extraction process, a novel filter design method with genetic algorithms is proposed. In addition, some ideas from previous improvements are used to build a faster searching strategy. Average accuracy of the original system was 69.78 and it was increased to 75.5 (without affecting time consumption) and 93.5 (with affecting time consumption)
- Keywords:
- Genetic Algorithm ; Indexing ; Spectrogram ; Frequency Spectrum ; Audio Fingerprinting ; Music Information Retrieval
Digital Object List-
محتواي کتاب - view
Bookmark