Top

BMC Psychiatry

Published in:

Open Access 01-12-2019 | Affective Disorder | Research article

Acoustic differences between healthy and depressed people: a cross-situation study

Authors: Jingying Wang, Lei Zhang, Tianli Liu, Wei Pan, Bin Hu, Tingshao Zhu

Published in: BMC Psychiatry | Issue 1/2019

Abstract

Background

Abnormalities in vocal expression during a depressed episode have frequently been reported in people with depression, but less is known about if these abnormalities only exist in special situations. In addition, the impacts of irrelevant demographic variables on voice were uncontrolled in previous studies. Therefore, this study compares the vocal differences between depressed and healthy people under various situations with irrelevant variables being regarded as covariates.

Methods

To examine whether the vocal abnormalities in people with depression only exist in special situations, this study compared the vocal differences between healthy people and patients with unipolar depression in 12 situations (speech scenarios). Positive, negative and neutral voice expressions between depressed and healthy people were compared in four tasks. Multiple analysis of covariance (MANCOVA) was used for evaluating the main effects of variable group (depressed vs. healthy) on acoustic features. The significances of acoustic features were evaluated by both statistical significance and magnitude of effect size.

Results

The results of multivariate analysis of covariance showed that significant differences between the two groups were observed in all 12 speech scenarios. Although significant acoustic features were not the same in different scenarios, we found that three acoustic features (loudness, MFCC5 and MFCC7) were consistently different between people with and without depression with large effect magnitude.

Conclusions

Vocal differences between depressed and healthy people exist in 12 scenarios. Acoustic features including loudness, MFCC5 and MFCC7 have potentials to be indicators for identifying depression via voice analysis. These findings support that depressed people’s voices include both situation-specific and cross-situational patterns of acoustic features.

Available only for authorised users

Cohen AS, Kim Y, Najolia GM. Psychiatric symptom versus neurocognitive correlates of diminished expressivity in schizophrenia and mood disorders. Schizophr Res. 2013;146:249–53. https://doi.org/10.1016/j.schres.2013.02.002.CrossRefPubMedPubMedCentral

American Psychiatric Association. Diagnostic and Statistical Manual of Mental Disorders (DSM-5®). Washington D.C: American Psychiatric Pub; 2013.

Cannizzaro M, Harel B, Reilly N, Chappell P, Snyder PJ. Voice acoustical measurement of the severity of major depression. Brain Cogn. 2004;56:30–5. https://doi.org/10.1016/j.bandc.2004.05.003.CrossRefPubMed

Kuny S, Stassen HH. Speaking behavior and voice sound characteristics in depressive patients during recovery. J Psychiatr Res. 1993;27:289–307. https://doi.org/10.1016/0022-3956(93)90040-9.CrossRefPubMed

Mundt JC, Vogel AP, Feltner DE, Lenderking WR. Vocal acoustic biomarkers of depression severity and treatment response. Biol Psychiatry. 2012;72:580–7. https://doi.org/10.1016/j.biopsych.2012.03.015.CrossRefPubMedPubMedCentral

Stassen HH, Kuny S, Hell D. The speech analysis approach to determining onset of improvement under antidepressants. Eur Neuropsychopharmacol. 1998;8:303–10. https://doi.org/10.1016/S0924-977X(97)00090-4.CrossRefPubMed

Cohn JF, Kruez TS, Matthews I, Yang Y, Nguyen MH, Padilla MT, et al. Detecting depression from facial actions and vocal prosody. In: 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops; 2009. p. 1–7.

Ee Brian Ooi K, Lech M, Brian Allen N. Prediction of major depression in adolescents using an optimized multi-channel weighted speech classification system. Biomed Signal Process Control. 2014;14(Supplement C):228–39. https://doi.org/10.1016/j.bspc.2014.08.006.CrossRef

Moore E II, Clements MA, Peifer JW, Weisser L. Critical analysis of the impact of glottal features in the classification of clinical depression in speech. IEEE Trans Biomed Eng. 2008;55:96–107.CrossRef

10.

Solomon C, Valstar MF, Morriss RK, Crowe J. Objective methods for reliable detection of concealed depression. Hum-Media Interact. 2015;2:5. https://doi.org/10.3389/fict.2015.00005.CrossRef

11.

Cohen AS, Elvevåg B. Automated computerized analysis of speech in psychiatric disorders. Curr Opin Psychiatry. 2014;27:203–9. https://doi.org/10.1097/YCO.0000000000000056.CrossRefPubMedPubMedCentral

12.

Cohen AS, Najolia GM, Kim Y, Dinzeo TJ. On the boundaries of blunt affect/alogia across severe mental illness: implications for research domain criteria. Schizophr Res. 2012;140:41–5. https://doi.org/10.1016/j.schres.2012.07.001.CrossRefPubMed

13.

Cohen AS, Lee Hong S, Guevara A. Understanding emotional expression using prosodic analysis of natural speech: refining the methodology. J Behav Ther Exp Psychiatry. 2010;41:150–7. https://doi.org/10.1016/j.jbtep.2009.11.008.CrossRefPubMed

14.

Alghowinem S, Goecke R, Wagner M, Epps J, Breakspear M, Parker G. Detecting depression: A comparison between spontaneous and read speech. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing; 2013. p. 7547–51.CrossRef

15.

Laukka P, Juslin P, Bresin R. A dimensional approach to vocal expression of emotion. Cogn Emot. 2005;19:633–53. https://doi.org/10.1080/02699930441000445.CrossRef

16.

Fu Q-J, Chinchilla S, Galvin JJ. The role of spectral and temporal cues in voice gender discrimination by Normal-hearing listeners and Cochlear implant users. J Assoc Res Otolaryngol. 2004;5:253–60. https://doi.org/10.1007/s10162-004-4046-1.CrossRefPubMedPubMedCentral

17.

Frances A. Diagnostic and statistical manual of mental disorders: DSM-IV. Washington D.C: American Psychiatric Association; 1994.

18.

Dibeklioglu H, Hammal Z, Cohn JF. Dynamic Multimodal Measurement of Depression Severity Using Deep Autoencoding. IEEE J Biomed Health Inform. 2017;22:1–1.

19.

Ellgring H, Scherer PKR. Vocal indicators of mood change in depression. J Nonverbal Behav. 1996;20:83–110. https://doi.org/10.1007/BF02253071.CrossRef

20.

Tolkmitt F, Helfrich H, Standke R, Scherer KR. Vocal indicators of psychiatric treatment effects in depressives and schizophrenics. J Commun Disord. 1982;15:209–22. https://doi.org/10.1016/0021-9924(82)90034-X.CrossRefPubMed

21.

Alpert M, Pouget ER, Silva RR. Reflections of depression in acoustic measures of the patient’s speech. J Affect Disord. 2001;66:59–69. https://doi.org/10.1016/S0165-0327(00)00335-9.CrossRefPubMed

22.

Mandal MK, Srivastava P, Singh SK. Paralinguistic characteristics of speech in schizophrenics and depressives. J Psychiatr Res. 1990;24:191–6. https://doi.org/10.1016/0022-3956(90)90059-Y.CrossRefPubMed

23.

Naarding P, Broek WW van den, Wielaert S, Harskamp F van. Aprosodia in major depression. J Neurolinguistics. 2003;16:37–41. doi: 10.1016/S0911-6044(01)00043-4.

24.

Kohler CG, Martin EA, Milonova M, Wang P, Verma R, Brensinger CM, et al. Dynamic evoked facial expressions of emotions in schizophrenia. Schizophr Res. 2008;105:30–9. https://doi.org/10.1016/j.schres.2008.05.030.CrossRefPubMedPubMedCentral

25.

Renneberg B, Heyn K, Gebhard R, Bachmann S. Facial expression of emotions in borderline personality disorder and depression. J Behav Ther Exp Psychiatry. 2005;36:183–96. https://doi.org/10.1016/j.jbtep.2005.05.002.CrossRefPubMed

26.

Eyben F, Weninger F, Gross F, Schuller B. Recent developments in openSMILE, the Munich open-source multimedia feature extractor. In: Proceedings of the 21st ACM international conference on multimedia. New York: ACM; 2013. p. 835–8. https://doi.org/10.1145/2502081.2502224.CrossRef

27.

Mundt JC, Snyder PJ, Cannizzaro MS, Chappie K, Geralts DS. Voice acoustic measures of depression severity and treatment response collected via interactive voice response (IVR) technology. J Neurolinguistics. 2007;20:50–64. https://doi.org/10.1016/j.jneuroling.2006.04.001.CrossRefPubMedPubMedCentral

28.

Cummins N, Epps J, Breakspear M, Goecke R. An investigation of depressed speech detection: features and normalization; 2011. p. 2997–3000.

29.

Gupta R, Malandrakis N, Xiao B, Guha T, Van Segbroeck M, Black M, et al. Multimodal prediction of affective dimensions and depression in human-computer interactions. In: Proceedings of the 4th international workshop on audio/visual emotion challenge. New York: ACM; 2014. p. 33–40. https://doi.org/10.1145/2661806.2661810.CrossRef

30.

Taguchi T, Tachikawa H, Nemoto K, Suzuki M, Nagano T, Tachibana R, et al. Major depressive disorder discrimination using vocal acoustic features. J Affect Disord. 2018;225(Supplement C):214–20. https://doi.org/10.1016/j.jad.2017.08.038.CrossRefPubMed

31.

Schuller B, Steidl S, Batliner A, Burkhardt F, Devillers L, Müller C, et al. The INTERSPEECH 2010 paralinguistic challenge. In: In Proc. Interspeech; 2010.

32.

Chiou BC, Chen CP. Feature space dimension reduction in speech emotion recognition using support vector machine. In: 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference; 2013. p. 1–6.

33.

Schuller B, Villar RJ, Rigoll G, Lang M. Meta-Classifiers in Acoustic and Linguistic Feature Fusion-Based Affect Recognition. In: Proceedings. (ICASSP ‘05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005; 2005. p. 325–8.CrossRef

34.

Dhall A, Goecke R, Joshi J, Wagner M, Gedeon T. Emotion recognition in the wild challenge 2013. In: Proceedings of the 15th ACM on international conference on multimodal interaction. New York: ACM; 2013. p. 509–16. https://doi.org/10.1145/2522848.2531739.CrossRef

35.

Tabachnick BG, Fidell LS. Multivariate analysis of variance and covariance. In: Using multivariate statistics. New York: Pearson; 2007. p. 402–7.

36.

Cohen J. Statistical power analyses for the behavioral sciences. 2nd ed. Hillsdale: Lawrence Erlbaum Associates; 1988.

37.

Zhu Y, Kim YC, Proctor MI, Narayanan SS, Nayak KS. Dynamic 3-D visualization of vocal tract shaping during speech. IEEE Trans Med Imaging. 2013;32:838–48.CrossRef

38.

Keedwell PA, Andrew C, Williams SCR, Brammer MJ, Phillips ML. The neural correlates of anhedonia in major depressive disorder. Biol Psychiatry. 2005;58:843–53. https://doi.org/10.1016/j.biopsych.2005.05.019.CrossRefPubMed

39.

Burton MW. The role of inferior frontal cortex in phonological processing. Cogn Sci. 2001;25:695–709.CrossRef

40.

Paulesu E, Goldacre B, Scifo P, Cappa SF, Gilardi MC, Castiglioni I, et al. Functional heterogeneity of left inferior frontal cortex as revealed by fMRI. NeuroRep. 1997;8:2011 https://journals.lww.com/neuroreport/Abstract/1997/05260/Functional_heterogeneity_of_left_inferior_frontal.42.aspx. Accessed 2 Aug 2018.CrossRef

41.

Yang Y, Fairbairn C, Cohn JF. Detecting depression severity from vocal prosody. IEEE Trans Affect Comput. 2013;4:142–50.CrossRef

42.

Scherer KR. Voice, Stress, and Emotion. In: Dynamics of Stress. Boston: Springer; 1986. p. 157–79. https://doi.org/10.1007/978-1-4684-5122-1_9.CrossRef

43.

Cummins N, Scherer S, Krajewski J, Schnieder S, Epps J, Quatieri TF. A review of depression and suicide risk assessment using speech analysis. Speech Commun. 2015;71:10–49. https://doi.org/10.1016/j.specom.2015.03.004.CrossRef

44.

Rottenberg J, Gross JJ, Gotlib IH. Emotion context insensitivity in major depressive disorder. J Abnorm Psychol. 2005;114:627–39.CrossRef

45.

Vogt T, Andre E. Improving automatic emotion recognition from speech via gender differentiation. LREC. 2006. p. 1123–6.

46.

Kendler KS, Gardner CO, Prescott CA. Toward a comprehensive developmental model for major depression in men. Am J Psychiatry. 2006;163:115–24. https://doi.org/10.1176/appi.ajp.163.1.115.CrossRefPubMed

47.

Kendler KS, Gardner CO, Prescott CA. Toward a comprehensive developmental model for major depression in women. FOCUS. 2005;3:83–97. https://doi.org/10.1176/foc.3.1.83.CrossRef

48.

Zimmerman FJ, Katon W. Socioeconomic status, depression disparities, and financial strain: what lies behind the income-depression relationship? Health Econ. 2005;14:1197–215.CrossRef

49.

Ohala JJ. Cross-language use of pitch: an ethological view. Phonetica. 1983;40:1–18. https://doi.org/10.1159/000261678.CrossRefPubMed

Title: Acoustic differences between healthy and depressed people: a cross-situation study
Authors: Jingying Wang
Lei Zhang
Tianli Liu
Wei Pan
Bin Hu
Tingshao Zhu
Publication date: 01-12-2019
Publisher: BioMed Central
Keywords: Affective Disorder
Affective Disorder
Published in: BMC Psychiatry / Issue 1/2019
Electronic ISSN: 1471-244X
DOI: https://doi.org/10.1186/s12888-019-2300-7

At a glance: The STEP trials

Springer Medicine

Acoustic differences between healthy and depressed people: a cross-situation study

Abstract

Background

Methods

Results

Conclusions

At a glance: The STEP trials

Springer Medicine

Abstract

Background

Methods

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 1/2019

Nightmare experience and family relationships in healthy volunteers and nightmare disorder patients

Satisfaction of family members with inpatient psychiatric care and its correlates: a national survey in China

Complementary and alternative medicine use in adults with autism spectrum disorder in Germany: results from a multi-center survey

Multivariate classification of drug-naive obsessive-compulsive disorder patients and healthy controls by applying an SVM to resting-state functional MRI data

The missing voice of engagement: an exploratory study from the perspectives of case-managers at an early intervention service for first-episode psychosis

First known case of catatonia due to cyclosporine A-related neurotoxicity in a pediatric patient with steroid-resistant nephrotic syndrome