Onset detection using leared dictionary by K-SVD

Author

Wenming Gui ; Xi Shao

Author_Institution

Jinling Inst. of Technol., Nanjing, China

fYear

2014

fDate

29-30 Sept. 2014

Firstpage

406

Lastpage

409

Abstract

This paper presents a promising and novel onset detection algorithm. Instead of traditional musical signal processing methods based on orthogonal transform such as Fourier Transform and Wavelet Transform, we focused on sparse representation with learned dictionary by K-SVD. We discussed the theorem and the methods of K-SVD for onset detection. The experimental results indicted that the proposed approach was theoretically feasible and practically effective.

Keywords

Fourier transforms; audio signal processing; dictionaries; music; signal detection; signal representation; singular value decomposition; wavelet transforms; Fourier transform; K-SVD; learned dictionary; musical audio; musical signal processing methods; onset detection algorithm; orthogonal transform; sparse representation; wavelet transform; Algorithm design and analysis; Dictionaries; Feature extraction; Matching pursuit algorithms; Signal processing algorithms; Transforms; Vectors; K-SVD; analytic dictionary; learned dictionary; note onset detection; sparse representation;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Research and Technology in Industry Applications (WARTIA), 2014 IEEE Workshop on

Conference_Location

Ottawa, ON

Type

conf

DOI

10.1109/WARTIA.2014.6976281

Filename

6976281

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=176545