Investigation of the Accuracy of Depression Prediction Based on Speech Processing

Kiss, Gábor; Jenei, Attila Zoltán

doi:10.1109/tsp49548.2020.9163495

Cited by 6 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We selected this because several studies have shown that using SVMs can give good results in the automatic recognition of depression ( 8 – 10 ). However, their use is not necessary, similar results can be obtained with other machine learning methods ( 18 , 19 , 32 , 33 ). The LibSVM ( 34 ) SVR implementation was used with radial basis function (rbf) kernel.…”

Section: Methodssupporting

confidence: 53%

See 1 more Smart Citation

The applicability of the Beck Depression Inventory and Hamilton Depression Scale in the automatic recognition of depression based on speech signal processing

et al. 2022

View full text Add to dashboard Cite

Depression is a growing problem worldwide, impacting on an increasing number of patients, and also affecting health systems and the global economy. The most common diagnostical rating scales of depression are self-reported or clinician-administered, which differ in the symptoms that they are sampling. Speech is a promising biomarker in the diagnostical assessment of depression, due to non-invasiveness and cost and time efficiency. In our study, we try to achieve a more accurate, sensitive model for determining depression based on speech processing. Regression and classification models were also developed using a machine learning method. During the research, we had access to a large speech database that includes speech samples from depressed and healthy subjects. The database contains the Beck Depression Inventory (BDI) score of each subject and the Hamilton Rating Scale for Depression (HAMD) score of 20% of the subjects. This fact provided an opportunity to compare the usefulness of BDI and HAMD for training models of automatic recognition of depression based on speech signal processing. We found that the estimated values of the acoustic model trained on BDI scores are closer to HAMD assessment than to the BDI scores, and the partial application of HAMD scores instead of BDI scores in training improves the accuracy of automatic recognition of depression.

show abstract

Section: Methodssupporting

confidence: 53%

“…In the present research we used the Hungarian Depressed Speech Database (DEPISDA) ( 19 ). The database currently contains speech samples of 218 (144 females and 74 males) Hungarian subjects (depressed and healthy subjects).…”

Section: Methodsmentioning

confidence: 99%

The applicability of the Beck Depression Inventory and Hamilton Depression Scale in the automatic recognition of depression based on speech signal processing

et al. 2022

View full text Add to dashboard Cite

show abstract

“…An experienced clinician can subjectively perceive the vocal changes typical of depression, but the practice is not based on the assessment of objective voice parameters. However, with regard to the close relation between voice and emotions, scientists are becoming increasingly interested in determining the ways to detect mental disorders through speech signals, i.e., creating an algorithm for detecting depression with great precision (Alghowinem et al, 2013;Afshan et al, 2018;Cummins et al, 2015;Cummins et al, 2011;He & Cao, 2018;Jiang et al, 2017;Kiss & Jenei, 2020;Lopez-Otero & Docio-Fernandez, 2020;Nunes et al, 2010;Rejaibi et al, 2022;Sturim et al, 2011;Xing et al, 2022). Such studies on depression are suitable since they are not intrusive, do not require direct contact with participants, and are not expensive (Cummins et al, 2011).…”

Section: Depression and Acoustic Features Of Voicementioning

confidence: 99%

Acoustic features of voice in adults suffering from depression

Calić¹,

Petrović-Lazić²,

Mentus³

et al. 2022

Psihol istraživanja

View full text Add to dashboard Cite

In order to examine the differences in people suffering from depression (EG, N=18) compared to the healthy controls (CG1, N=24) and people with the diagnosed psychogenic voice disorder (CG2, N=9), nine acoustic features of voice were assessed among the total of 51 participants using the MDVP software programme ("Kay Elemetrics" Corp., model 4300). Nine acoustic parameters were analysed on the basis of the sustained phonation of the vowel /a/. The results revealed that the mean values of all acoustic parameters differed in the EG compared to both the CG1 and CG2 as follows: the parameters which indicate frequency variability (Jitt, PPQ), amplitude variability (Shim, vAm, APQ) and noise and tremor parameters (NHR, VTI) were higher; only the parameters of fundamental frequency (F0) and soft index phonation (SPI) were lower (F0 compared to CG1, and SPI compared to CG1 and CG2). Only the PPQ parameter was not significant. vAm and APQ had the highest discriminant value for depression. The acoustic features of voice, analysed in this study with regard to the sustained phonation of a vowel, were different and discriminant in the EG compared to CG1 and CG2. In voice analysis, the parameters vAm and APQ could potentially be the markers indicative of depression. The results of this research point to the importance of the voice, that is, its acoustic indicators, in recognizing depression. Important parameters that could help create a programme for the automatic recognition of depression are those from the domain of voice intensity variation.

show abstract