Voice signal processing for patiens with stroke hospitalisation

Recently, gradual rise of significance signal processing in clinical applications has been observed. The paper is focused in human voices changes as a stroke result. We suppose that signal processing could be useful to monitor of hospitalization and rehabilitation progress. The voice of several patients has been recorded; afterwards the analysis of these samples has been performed, by using various algorithms. Numerical data are assigned to patient state of health during recording and are compared with data of healthful human of the same age group and gender. Time domain, frequency and mixed time-frequency analysis have been applied. As a result of the work, an algorithm of treatment progress estimation was proposed. The algorithm can be easily adapted to medical environment. Chosen sets of results are shown in this paper. Examples, presented in the paper, are representative for middle age patients.