Title :
Separation of musical instruments using correntropy
Author :
Zbek, M. Erdal Ö ; Savaci, F. Acar
Author_Institution :
Elektrik-Elektron. Muhendisligi Bolumu, Izmir Yuksek Teknoloji Enstitusu, Izmir
Abstract :
Recently, a generalized correlation function called correntropy, extracting both the time structure and the statistical distribution of time series using kernel methods, have been proposed. In this work, the statistically independence criterion obtained using correntropy has been used in separation of different musical instrument samples playing the same note.
Keywords :
acoustic signal processing; correlation methods; entropy; musical instruments; statistical distributions; time series; correntropy; generalized correlation function; kernel methods; musical instrument separation; statistical distribution; statistically independence criterion; time series; time structure; Instruments; Kernel; Model driven engineering; Statistical distributions;
Conference_Titel :
Signal Processing, Communication and Applications Conference, 2008. SIU 2008. IEEE 16th
Conference_Location :
Aydin
Print_ISBN :
978-1-4244-1998-2
Electronic_ISBN :
978-1-4244-1999-9
DOI :
10.1109/SIU.2008.4632652