Abstract-Evaluation of speakers who are high-risk suicidal compared to those with less clinical depression are critical when the syndrome underlying a patient's abnormal behaviour is diagnosed without expertise. This study describes a way to classify the speech samples collected from groups of depressive and suicidal speakers by employing the speech processing technique in data analysis. First, the Glottal Spectral Slope (GSS) and Mel-Frequency Cepstral Coefficients (MFCC) were computationally estimated from the voiced segments detected from the categorized speech sample database. Second, the pairwise classification was then made on the combination of those extracted vocal features respectively corresponding to the frequency response of the source and the filter in speech production system model.The procedure of this research was carried out in order to investigate the discriminative property of the focused vocal parameters mainly between depressed speakers and high-risk suicidal speaker groups. The result revealed that MFCC and GSS parameters are slightly high effective in term of vocal indicator corresponding to severe depression with fairly high performance in between-group separation.Index Terms-Depression, glottal spectral slope, MFCC, speech. I. INTRODUCTIONSuicide is a major public health problem in mostly every society. The number of people who died by committing suicide is increasing up every year. This kind of tragedy has been reported to be among the leading cause of death with growing dead toll rate. As acknowledged from the statistics reported publically, suicide remains frequent but preventable cause of death with in-time recue or earlier diagnosis and admission into the care-taking program in hospitals before the lethal risk of suicide will elevate. Therefore prevention is currently a solely way to be made to save life of people from such tragedy. Screening patients who are at risk of committing suicide is very important task and only possibly completed by the psychiatrist with high expertise. In addition, the suicide prevention program is presently limited to clinical level which consumes time and bases heavily on the psychiatrist's experience and judgment. In this work what we found from data processing and speech analysis could lead to be additionally one of supplements to the suicide prevention program. In the past, many research groups have been attempting to figure out the way to identify individual categorized groups of patients with emotional disorders and the various methodologies have been conducted to reach the conclusion. The most popular technique emerging in area of speech processing has been taken in account of research procedure to accomplish the specific tasks such as data processing, information retrieval and feature extraction prior to analysis and interpretation of results.Severely depressive persons at near-term suicidal risk exhibit the perceptual changes significantly in their vocal qualities that can distinguish them from normal ones [1]. In formerly published papers [2]-[6...

No abstract

No abstract