Pemisahan sumber-sumber suara tercampur berdasarkan penelusuran frekuensi dasar pada sinyal wicara dan musik

Sound source separation is challenging problem in acoustics area. The problem comes from the cocktail party, presence of multi talker and the ability of human ear to focus and separate voice from many sources. Some approaches have been developed to separate mixed sound from sources. The estimation of fundamental frequency is one of approach to decompose mixture sounds into its components based on its harmonics. The idea is by grouping the components which has the same harmonics from the mixture sound by pitch and common amplitude modulation and harmonic selection technique. The estimation of fundamental frequency itself is challenging problem which in progress as well as sound separation problem. The result of those methods clearly shown that F0-based sound separation works efficiently, especially in musical sounds. However, the method needs to be improved in other conditions such as noisy and reverberant.

Full paper (in Indonesian language) can be downloaded here.
Matlab source code can be obtained from here.