I examine in my dissertation the differences between acoustic parameters of healthy persons and persons diagnosed with depression, in case of reading a fixed text. Diagnosis of depression in a proper time may even help lives. According to the opinion of psychiatrists, a difference can occur in depressed speech on the basis of hearing, too, as in an acoustic product. Purpose of my dissertation is to detect acoustic features of speech, which can effectively separate healthy and depressed groups from each other.
I made records for my dissertation with patients suffering from depression at Department of Psychiatry of Semmelweis Clinic, which were segmented at a phoneme level. I gained the following parameters from these records, and from the earlier segmented records of healthy persons available at our Department with the help of PRAAT program: basic frequency and first and second formant frequency of “E” sound, intensity fluctuation, register, full pause length, full duration of record, ration of full pause compared to duration of record, number of phonemes, speech rate, articulation rate, ratio of pauses and voiced sounds, ratio of voiced and unvoiced sounds.
I made representation of acoustic features of the two groups with the help of column diagrams, while their analysis was made with a statistical analysis. I used a two-patterned T-trial for the statistical analysis.
I identified successfully in my dissertation acoustic parameters, which are applicable for the separation of the two groups from each other. Results are promising, and they could stimulate for further researches.