Signal Enhancement By Single Channel Source Separation

Most gadgets and electronics devices are commonly equipped with single microphone only. This is difficult task in source separation world which traditionally required more sensors than sources to achieve better performance. In this paper we evaluated single channel source separation to enhance target signal from inteferred noise. The method we used is non-negative matrix factorization (NMF) that decompose signal into its components and find the matched signal to target speaker. As objective evaluation, coherence score is used to measure the perceptual similarity from enhanced to original one. It show the extracted has 0.5 of average coherence that shows medium correlation between both signals.

The following slides talk a bit about signal Signal enhancement by single channel source separation principle. You can grab the full paper here.

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.

On Performance of Two-Sensor Sound Separation Methods Including Binaural Processors

Human beings have binaural inputs to separate and localize sound sources. Those two functions of binaural hearing can not be easily transformed to the computational methods. In this paper, three conventional methods to separate target signal from interfering noise are compared. Those methods include a binaural model, an independent component analysis (ICA) and a time-frequency masking applied to ICA. Performances were compared by means of spectrograms as well as coherence.

Above is abstract of my paper presented in ASJ Kyushu Chapter, November 25, 2011, in Oita - Japan. You can see the poster below (click to enlarge).

Full paper is available by request.