The aim of the diploma project is to find a method through which it will be possibleto classify the selected emotion from speech. At the beginning of the work deals with the description of the human body and their voice-generating operation. Furthermore, the text deals with the problem of the human voice into digital form.Great attention is paid to the parameters of the speech signal with an emphasis on describing the symptoms to help the selected emotion. The work deals with therecognition of emotions and a description of some of them. The main part is finding the best methods to reduce symptoms of segmental and suprasegmental speech utterances. The results of success was achieved by comparing the classification of selected emotions when using multiple methods and compare their results. The most important criterion in assessing the results ofthe reduction parameters of the speech signal, based on previous research in this area.