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.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call