Application of standard algorithms of automatic signal separation in medicine

In the present article various methods of automatic separation of acoustic signals have been described. The biggest focus was placed on two methods, Blind signal Separation (BSS) and Independent Component Analysis (ICA). In order to verify the efficacy of these methods, selected separation algorithms have been used for deconvolution of a specially prepared sinusoidal and saw-tooth sound signals as well as natural signals such as recordings of human voice. The obtained results have been compared and presented. More accurate results have been acquired from the analysis of artificially prepared signals that is the sinusoidal and saw-tooth signals which were mixed together using numerical transformations. Due to the potential practical usage of speech signal separation in medicine, more stress has been put on the analysis of life taken signals, which were created by mixing voices of few persons speaking simultaneously. The assessment of the usability of different algorithms, which effected from the research, may have practical application due to the fact that in the available literature the authors usually limit themselves only to presenting (and praising) algorithms created on their own, scarcely mentioning algorithms of different authors predominantly without doing necessary comparative researches. These missing researches constitute the essential part of the work presented in this article.