Detecting Depression in Speech Under Different Speaking Styles and Emotional Valences

Detecting depression in speech is a hot topic in recent years. Some inconsistent results in previous researches imply a few important influence factors are ignored. In this paper, we investigated a sample of 184 subjects (108 females, 76 males) to examine the influence of speaking style and emotional valence on depression detection. First, classification accuracy was used to measure the influence of these two factors. Then, two-way analysis of variance was employed to determine interactive acoustical features. Finally, normalized features by subtracting got higher classification accuracies. Results show that both speaking style and emotional valence are important factors. Spontaneous speech is better than automatic speech and neutral is the best choice among three emotional valences in depression detection. Normalized features improve the detection performance.

[1]  W W Zung,et al.  Self-rating depression scale in an outpatient clinic. Further validation of the SDS. , 1965, Archives of general psychiatry.

[2]  Zvia Breznitz,et al.  Effects of accelerated reading rate on memory for text , 1992 .

[3]  Nicholas B. Allen,et al.  Detection of Clinical Depression in Adolescents’ Speech During Family Interactions , 2011, IEEE Transactions on Biomedical Engineering.

[4]  Susan L. Rossell,et al.  Auditory verbal hallucinations in bipolar disorder (BD) and major depressive disorder (MDD): A systematic review. , 2015, Journal of affective disorders.

[5]  Eliathamby Ambikairajah,et al.  Spectro-temporal analysis of speech affected by depression and psychomotor retardation , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  J Sundberg,et al.  Measuring the rate of change of voice fundamental frequency in fluent speech during mental depression. , 1988, The Journal of the Acoustical Society of America.

[7]  Elmar Nöth,et al.  Automatic modelling of depressed speech: relevant features and relevance of gender , 2014, INTERSPEECH.

[8]  D. Mitchell Wilkes,et al.  Investigation of vocal jitter and glottal flow spectrum as possible cues for depression and near-term suicidal risk , 2004, IEEE Transactions on Biomedical Engineering.

[9]  Klaus R. Scherer,et al.  Vocal indicators of mood change in depression , 1996 .

[10]  Fernando De la Torre,et al.  Detecting depression from facial actions and vocal prosody , 2009, 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops.

[11]  J P Watson,et al.  Effects of communication content on speech behavior of depressives. , 1992, Comprehensive psychiatry.

[12]  Elliot Moore,et al.  Critical Analysis of the Impact of Glottal Features in the Classification of Clinical Depression in Speech , 2008, IEEE Transactions on Biomedical Engineering.

[13]  M. Hamilton.  A RATING SCALE FOR DEPRESSION , 1960, Journal of neurology, neurosurgery, and psychiatry.

[14]  Yang Ling,et al.  Effect of Tryptophan Hydroxylase-2 rs7305115 SNP on suicide attempts risk in major depression , 2010, Behavioral and Brain Functions.

[15]  Luo Yuejia,et al.  Revision of the Chinese Facial Affective Picture System , 2011 .

[16]  Nicholas B. Allen,et al.  Multichannel Weighted Speech Classification System for Prediction of Major Depression in Adolescents , 2013, IEEE Transactions on Biomedical Engineering.

[17]  Louis-Philippe Morency,et al.  Audiovisual behavior descriptors for depression assessment , 2013, ICMI '13.

[18]  R. Davidson,et al.  Depression: perspectives from affective neuroscience. , 2002, Annual review of psychology.

[19]  M. Salimi,et al.  Identifying depressed from healthy cases using speech processing , 2012, 2012 19th Iranian Conference of Biomedical Engineering (ICBME).

[20]  R. Spitzer,et al.  The PHQ-9 , 2001, Journal of General Internal Medicine.

[21]  Linda Smolak,et al.  The Relationship of Gender and Voice to Depression and Eating Disorders , 2002 .

[22]  J. Mundt,et al.  Vocal Acoustic Biomarkers of Depression Severity and Treatment Response , 2012, Biological Psychiatry.

[23]  F Angeleri,et al.  The Influence of Depression, Social Activity, and Family Stress on Functional Outcome After Stroke , 1993, Stroke.

[24]  B. Sahakian,et al.  Neurocognitive mechanisms in depression: implications for treatment. , 2009, Annual review of neuroscience.

[25]  J. Mundt,et al.  Voice acoustic measures of depression severity and treatment response collected via interactive voice response (IVR) technology , 2007, Journal of Neurolinguistics.

[26]  D. Kupfer,et al.  Interval between onset of sleep and rapid-eye-movement sleep as an indicator of depression. , 1972, Lancet.

[27]  Haizhou Li,et al.  Dimension reduction of the modulation spectrogram for speaker verification , 2008, Odyssey.

[28]  Tamás D. Gedeon,et al.  A comparative study of different classifiers for detecting depression from spontaneous speech , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[29]  R Jouvent,et al.  Decreased presynaptic dopamine function in the left caudate of depressed patients with affective flattening and psychomotor retardation. , 2001, The American journal of psychiatry.

[30]  J. Schweitzer,et al.  Owner reports of attention, activity, and impulsivity in dogs: a replication study , 2010, Behavioral and Brain Functions.

[31]  Roland Göcke,et al.  An Investigation of Depressed Speech Detection: Features and Normalization , 2011, INTERSPEECH.

[32]  M. Alpert,et al.  Reflections of depression in acoustic measures of the patient's speech. , 2001, Journal of affective disorders.

[33]  A. Calev,et al.  Retrieval from semantic memory using meaningful and meaningless constructs by depressed, stable bipolar and manic patients. , 1989, The British journal of clinical psychology.