A Privacy-Oriented Approach for Depression Signs Detection Based on Speech Analysis

Abstract

Currently, AI-based assistive technologies, particularly those involving sensitive data, such as systems for detecting mental illness and emotional disorders, are full of confidentiality, integrity, and security compromises. In the aforesaid context, this work proposes an algorithm for detecting depressive states based on only three never utilized speech markers. This reduced number of markers offers a valuable protection of personal (sensitive) data by not allowing for the retrieval of the speaker’s identity. The proposed speech markers are derived from the analysis of pitch variations measured in speech data obtained through a tale reading task performed by typical and depressed subjects. A sample of 22 subjects (11 depressed and 11 healthy, according to both psychiatric diagnosis and BDI classification) were involved. The reading wave files were listened to and split into a sequence of intervals, each lasting two seconds. For each subject’s reading and each reading interval, the average pitch, the pitch variation (T), the average pitch variation (A), and the inversion percentage (also called the oscillation percentage O) were automatically computed. The values of the triplet (Ti, Ai, Oi) for the i-th subject provide, all together, a 100% correct discrimination between the speech produced by typical and depressed individuals, while requiring a very low computational cost and offering a valuable protection of personal data.

A Dynamic Probabilistic Model for Heterogeneous Data Fusion: A Pilot Case Study from Computer-Aided Detection of Depression

“…Now, system ( 9 ) can be easily solved if one has enough time and patience, or simply a computer. Nevertheless, the general case will be left aside and the above procedure will be now applied to a reference sample already used to the same aim in [ 34 ]. It could be objected that the considered sample cannot be defined “sufficiently large”.…”

“…The above procedure can be reproduced step by step for each of the two remaining parameters A and O . One only needs to insert in system ( 11 ) the values of resulting from Tables 1–6 in [ 34 ] for these parameters. These values are listed in the following Table 1 (while, for the sake of completeness, the intervals and are specified for all the three parameters T , A and O in Table 2 , Table 3 and Table 4 ).…”

“…This point will be discussed in details in the following Sections. More precisely, in Section 2 and Section 3 , the formulation of the «discretized» model is presented, in Section 4 , Section 5 and Section 6 , the language to the detection of depression using the results reported in [ 34 ] is applied, and in Section 7 some possible research perspectives are outlined.…”