Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Background
Method
Data Collection and Preparation
Statistical Test
Results
Classification Results
Statistical Results
Conclusions
Acknowledgement
References

Characterising depressed speech for classification

Profile image of Sharifa AlghowinemSharifa Alghowinem

Abstract

Depression is a serious psychiatric disorder that affects mood, thoughts, and the ability to function in everyday life. This paper investigates the characteristics of depressed speech for the purpose of automatic classification by analysing the effect of different speech features on the classification results. We analysed voiced, unvoiced and mixed speech in order to gain a better understanding of depressed speech and to bridge the gap between physiological and affective computing studies. This understanding may ultimately lead to an objective affective sensing system that supports clinicians in their diagnosis and monitoring of clinical depression. The characteristics of depressed speech were statistically analysed using ANOVA and linked to their classification results using GMM and SVM. Features were extracted and classified over speech utterances of 30 clinically depressed patients against 30 controls (both gender-matched) in a speaker-independent manner. Most feature classification results were consistent with their statistical characteristics, providing a link between physiological and affective computing studies. The classification results from low-level features were slightly better than the statistical functional features, which indicates a loss of information in the latter. We found that both mixed and unvoiced speech were as useful in detecting depression as voiced speech, if not better.

Related papers

From Joyous to Clinically Depressed: Mood Detection Using Spontaneous Speech
Roland Goecke

2012

Depression and other mood disorders are common and disabling disorders. We present work towards an objective diagnostic aid supporting clinicians using affective sensing technology with a focus on acoustic and statistical features from spontaneous speech. This work investigates differences in expressing positive and negative emotions in depressed and healthy control subjects as well as whether initial gender classification increases the recognition rate. To this end, spontaneous speech from interviews of 30 subjects of each depressed and controls was analysed, with a focus on questions eliciting positive and negative emotions. Using HMMs with GMMs for classification with 30-fold cross-validation, we found that MFCC, energy and intensity features gave highest recognition rates when female and male subjects were analysed together. When the dataset was first split by gender, root mean square energy and shimmer features, respectively, were found to give the highest recognition rates in females, while it was voice quality for males. Overall, correct recognition rates from acoustic features for depressed female subjects were higher than for male subjects. Using temporal features, we found that the response time and average syllable duration were longer in depressed subjects, while the interaction involvement and articulation rate wesre higher in control subjects.

View PDFchevron_right
Automatic Detection of Depressive States from Speech
Filomena Scibelli, Vincenzo Capuano

This paper investigates the acoustical and perceptual speech features that differentiate a depressed individual from a healthy one. The speech data gathered was a collection from both healthy and depressed subjects in the Italian language, each comprising of a read and spontaneous narrative. The pre-processing of this dataset was done using Mel Frequency Cepstral Coefficient (MFCC). The speech samples were further processed using Principal Component Analysis (PCA) for correlation and dimensionality reduction. It was found that both groups differed with respect to the extracted speech features. To distinguish the depressed group from the healthy one on the basis the proposed speech processing algorithm the Self Organizing Map (SOM) algorithm was used. The clustering accuracy given by SOM's was 80.67%.

View PDFchevron_right
Detection of Major Depressive Disorder Based on a Combination of Voice Features: An Exploratory Approach
Shuji S Shinohara

International Journal of Environmental Research and Public Health

In general, it is common knowledge that people’s feelings are reflected in their voice and facial expressions. This research work focuses on developing techniques for diagnosing depression based on acoustic properties of the voice. In this study, we developed a composite index of vocal acoustic properties that can be used for depression detection. Voice recordings were collected from patients undergoing outpatient treatment for major depressive disorder at a hospital or clinic following a physician’s diagnosis. Numerous features were extracted from the collected audio data using openSMILE software. Furthermore, qualitatively similar features were combined using principal component analysis. The resulting components were incorporated as parameters in a logistic regression based classifier, which achieved a diagnostic accuracy of ~90% on the training set and ~80% on the test set. Lastly, the proposed metric could serve as a new measure for evaluation of major depressive disorder.

View PDFchevron_right
An Investigation of Depressed Speech Detection: Features and Normalization
Roland Goecke

2011

In recent years, the problem of automatic detection of mental illness from the speech signal has gained some initial interest, however questions remaining include how speech segments should be selected, what features provide good discrimination, and ...

View PDFchevron_right
Depression Detection from Speech
Vishnu Vidyadharan

International Journal of Engineering Research and, 2020

Depression (Major Depressive Disorder) has become one of the most prevalent mental illness across the globe. It can be described as a state in which a person feels sad or loses interest in everyday activities which are normally considered enjoyable. It affects the thoughts and the way one feels about the people that he/she comes across. More than 260 million people throughout the world suffer from depression. This comprises of people belonging to all age groups. Depression can lead a person to hopelessness and subsequently result into suicide. It is also estimated that depression will account for the most common of diseases by 2030. Nearly 20% of people with untreated depressive disorder commit suicide. Therefore ways to detect depression are a major concern. The current diagnoses are highly inconsistent and expensive. The most common technique used to detect depression is comparing the words in a person's response to a questionnaire, with a database comprising of terms commonly used by depressed patients. This method has found to be inefficient in terms of its accuracy in prediction as well as the time consumed in diagnosis. In this project, a new method for early detection of depression is implemented. The features of speech which are associated with signs of depression can be traced by neural networks. Convolutional Neural Networks, in particular, can be applied to identify depression indicators in speech. Spectrograms, which mark the intensities of frequencies of speech can be given as input to Convolutional Neural Networks designed to learn similar patterns in depressed audio.

View PDFchevron_right
An investigation of linguistic stress and articulatory vowel characteristics for automatic depression classification
Roland Goecke

Computer Speech & Language

The effects of psychomotor retardation associated with clinical depression have been linked with a reduction in variability in acoustic parameters in previous work. However, despite opportunities for exploring this reduction through tightly coupled linguistic-acoustic analyses that are afforded by contemporary automatic systems, linguistic stress differences between nondepressed and clinically depressed individuals have yet to be investigated. In this paper, by examining regions within the vowel space corresponding to articulatory parameters, statistically significant differences in articulatory characteristics were discovered at a paraphonetic level. Considering linguistic stress components, depressed speakers exhibited shorter vowel durations and reductions in loudness, which were statistically significant for several articulatory characteristics, accompanied by less variance, especially for 'mid' positioned vowels. Results using a small set of linguistic stress based features derived from multiple vowel articulatory parameter sets generated gains of 7% in two-class depression classification performance of baseline approaches, for the DAIC-WOZ dataset. Further, linguistic stress feature results indicate that specific vowel set analysis provides better discrimination of clinically depressed and non-depressed speakers. Apart from improved classification, knowledge gleaned from this research can also be used for designing more effective depressed speech elicitation methods to be used in conjunction with automatic depression disorder speech assessment systems.

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

Frontiers in Psychiatry

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...

View PDFchevron_right
DEPRESSION SPEAKS: AUTOMATIC DISCRIMINATION BETWEEN DEPRESSED AND NON-DEPRESSED SPEAKERS BASED ON NONVERBAL SPEECH FEATURES
Filomena Scibelli

This article proposes an automatic approach-based on non-verbal speech features-aimed at the automatic discrimination between depressed and non-depressed speakers. The experiments have been performed over one of the largest corpora collected for such a task in the literature (62 patients diagnosed with depression and 54 healthy control subjects), especially when it comes to data where the depressed speakers have been diagnosed as such by professional psychiatrists. The results show that the discrimination can be performed with an accuracy of over 75% and the error analysis shows that the chances of correct classification do not change according to gender, depression-related pathology diagnosed by the psychiatrists or length of the pharmacological treatment (if any). Furthermore, for every depressed subject, the corpus includes a control subject that matches age, education level and gender. This ensures that the approach actually discriminates between depressed and non depressed speakers and does not simply capture differences resulting from other factors.

View PDFchevron_right

References (30)

  1. References
  2. U. D. of Health and H. Services, "Healthy people 2010: Under- standing and improving health," Health San Francisco, vol. 2nd, no. 46, p. 62 p., 2000.
  3. S. Baik, B. J. Bowers, L. D. Oakley, and J. L. Susman, "The recog- nition of depression: The primary care clinicians perspective," An- nals Of Family Medicine, vol. 3, no. 1, pp. 31-37, 2005.
  4. J. C. Mundt, P. J. Snyder, M. S. Cannizzaro, K. Chappie, and D. S. Geralts, "Voice acoustic measures of depression severity and treatment response collected via interactive voice response tech- nology," Journal of Neurolinguistics, vol. 20, no. 1, pp. 50-64, 2007.
  5. A. Nilsonne, "Speech characteristics as indicators of depressive illness," Acta Psychiatrica Scandinavica, vol. 77, no. 3, pp. 253- 263, 1988.
  6. S. Kuny and H. H. Stassen, "Speaking behavior and voice sound characteristics in depressive patients during recovery," Journal of Psychiatric Research, vol. 27, no. 3, pp. 289-307, 1993.
  7. H. Ellgring and K. R. Scherer, "Vocal indicators of mood change in depression," Journal of Nonverbal Behavior, vol. 20, no. 2, pp. 83-110, 1996.
  8. S. G. Koolagudi and K. S. Rao, "Emotion recognition from speech: a review," International Journal of Speech Technology, vol. 15, no. 3, pp. 37-40, 2011.
  9. A. J. Flint, S. E. Black, I. Campbell-Taylor, G. F. Gailey, and C. Levinton, "Abnormal speech articulation, psychomotor retar- dation, and subcortical dysfunction in major depression," Journal of Psychiatric Research, vol. 27, no. 3, pp. 309-319, Jul. 1993.
  10. E. Moore, M. Clements, J. Peifer, and L. Weisser, "Critical analy- sis of the impact of glottal features in the classification of clinical depression in speech." IEEE Trans. on Bio-medical Eng., vol. 55, no. 1, pp. 96-107, Jan. 2008.
  11. D. J. France, R. G. Shiavi, S. Silverman, M. Silverman, and D. M. Wilkes, "Acoustical properties of speech as indicators of depres- sion and suicidal risk." IEEE Trans. on bio-medical Eng., vol. 47, no. 7, pp. 829-37, Jul. 2000.
  12. K. R. Scherer, Vocal assessment of affective disorders. Lawrence Erlbaum Associates, 1987, pp. 57-82.
  13. A. Nunes, L. Coimbra, and A. Teixeira, "Voice quality of euro- pean portuguese emotional speech corresponding author," Com- putational Processing of the Portuguese Language Lecture Notes in Computer Science, vol. 6001/2010, pp. 142-151, 2010.
  14. L. A. Low, N. C. Maddage, M. Lech, L. B. Sheeber, and N. B. Allen, "Detection of clinical depression in adolescents speech dur- ing family interactions." IEEE Trans. on Biomedical Eng., vol. 58, no. 3, pp. 574-586, 2011.
  15. A. Ozdas, R. G. Shiavi, S. E. Silverman, M. K. Silverman, and D. M. Wilkes, "Investigation of vocal jitter and glottal flow spec- trum as possible cues for depression and near-term suicidal risk." IEEE Trans. on Biomedical Eng., vol. 51, no. 9, pp. 1530-1540, 2004.
  16. A. Ozdas, R. Shiavi, S. Silverman, M. Silverman, and D. Wilkes, "Analysis of fundamental frequency for near term suicidal risk assessment," IEEE Conf. Systems, Man, Cybernetics, pp. 1853- 1858, 2000.
  17. E. Moore, M. Clements, J. Peifer, and L. Weisser, "Comparing ob- jective feature statistics of speech for classifying clinical depres- sion," Proc. 26th Ann. Conf. Eng. Med. Biol., vol. 1, pp. 17-20, Jan. 2004.
  18. J. F. Cohn, T. S. Kruez, I. Matthews, Y. Yang, M. H. Nguyen, M. T. Padilla, F. Zhou, and F. De la Torre, "Detecting depression from facial actions and vocal prosody," 2009 3rd International Con- ference on Affective Computing and Intelligent Interaction and Workshops, pp. 1-7, Sep. 2009.
  19. N. Cummins, J. Epps, M. Breakspear, and R. Goecke, "An Inves- tigation of Depressed Speech Detection: Features and Normaliza- tion," in Proc. Interspeech, 2011, pp. 2997-3000.
  20. S. Alghowinem, R. Goecke, M. Wagner, J. Epps, M. Breakspear, and G. Parker, "From Joyous to Clinically Depressed: Mood De- tection Using Spontaneous Speech," in Proc. FLAIRS-25, 2012, accepted.
  21. K. E. B. Ooi, L.-S. A. Low, M. Lech, and N. Allen, "Early predic- tion of major depression in adolescents using glottal wave char- acteristics and teager energy parameters," in Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Con- ference on. IEEE, 2012, pp. 4613-4616.
  22. G. Zhou, J. H. Hansen, and J. F. Kaiser, "Classification of speech under stress based on features derived from the nonlinear tea- ger energy operator," in Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on, vol. 1. IEEE, 1998, pp. 549-552.
  23. S. Koolagudi and K. Rao, "Emotion recognition from speech: a review," International Journal of Speech Technology, pp. 1-19.
  24. Z. Zeng, M. Pantic, G. I. Roisman, and T. S. Huang, "A survey of affect recognition methods: audio, visual, and spontaneous ex- pressions." IEEE Trans. on PAMI, vol. 31, no. 1, pp. 39-58, 2007.
  25. S. Alghowinem, R. Goecke, M. Wagner, J. Epps, M. Breakspear, and G. Parker, "Detecting Depression: A Comparison between Spontaneous and Read Speech," in IEEE International Confer- ence on Acoustics, Speech and Signal Processing (ICASSP 2013), May 2013.
  26. F. Eyben, M. Wöllmer, and B. Schuller, "Opensmile: the munich versatile and fast open-source audio feature extractor," in Proc. ACM Multimedia (MM'10), Oct. 2010, pp. 1459-1462.
  27. M. Brookes et al., "Voicebox: Speech processing toolbox for matlab," Software, available [Mar. 2011] from www. ee. ic. ac. uk/hp/staff/dmb/voicebox/voicebox. html, 1997.
  28. S. Alghowinem, R. Goecke, M. Wagner, J. Epps, G. T, M. Breaks- pear, and G. Parker, "A Comparative Study of Different Classifiers for Detecting Depression from Spontaneous Speech," in IEEE In- ternational Conference on Acoustics, Speech and Signal Process- ing (ICASSP 2013), May 2013.
  29. B. Schuller, A. Batliner, S. Steidl, and D. Seppi, "Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge," Speech Communication, vol. 53, no. Feb, pp. 1062-1087, 2011.
  30. C. C. Chang and C. J. Lin, "Libsvm: a library for svm," 2006-03- 04]. http: www. csic. ntu. edu. tw/rcjlin/papers/lib. svm, pp. 1-30, 2001.

Related papers

An Investigation of Emotional Speech in Depression Classification
Roland Goecke

Interspeech 2016, 2016

Assessing depression via speech characteristics is a growing area of interest in quantitative mental health research with a view to a clinical mental health assessment tool. As a mood disorder, depression induces changes in response to emotional stimuli, which motivates this investigation into the relationship between emotion and depression affected speech. This paper investigates how emotional information expressed in speech (i.e. arousal, valence, dominance) contributes to the classification of minimally depressed and moderately-severely depressed individuals. Experiments based on a subset of the AVEC 2014 database show that manual emotion ratings alone are discriminative of depression and combining rating-based emotion features with acoustic features improves classification between mild and severe depression. Emotion-based data selection is also shown to provide improvements in depression classification and a range of threshold methods are explored. Finally, the experiments presented demonstrate that automatically predicted emotion ratings can be incorporated into a fully automatic depression classification to produce a 5% accuracy improvement over an acoustic-only baseline system.

View PDFchevron_right
Detecting depression: A comparison between spontaneous and read speech
Gordon Parker, Sharifa Alghowinem, Roland Goecke

2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013

Major depressive disorders are mental disorders of high prevalence, leading to a high impact on individuals, their families, society and the economy. In order to assist clinicians to better diagnose depression, we investigate an objective diagnostic aid using affective sensing technology with a focus on acoustic features. In this paper, we hypothesise that (1) classifying the general characteristics of clinical depression using spontaneous speech will give better results than using read speech, (2) that there are some acoustic features that are robust and would give good classification results in both spontaneous and read, and (3) that a 'thin-slicing' approach using smaller parts of the speech data will perform similarly if not better than using the whole speech data. By examining and comparing recognition results for acoustic features on a real-world clinical dataset of 30 depressed and 30 control subjects using SVM for classification and a leave-one-out cross-validation scheme, we found that spontaneous speech has more variability, which increases the recognition rate of depression. We also found that jitter, shimmer, energy and loudness feature groups are robust in characterising both read and spontaneous depressive speech. Remarkably, thin-slicing the read speech, using either the beginning of each sentence or the first few sentences performs better than using all reading task data.

View PDFchevron_right
A comparative study of different classifiers for detecting depression from spontaneous speech
Gordon Parker, Sharifa Alghowinem, Roland Goecke

2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013

Accurate detection of depression from spontaneous speech could lead to an objective diagnostic aid to assist clinicians to better diagnose depression. Little thought has been given so far to which classifier performs best for this task. In this study, using a 60-subject real-world clinically validated dataset, we compare three popular classifiers from the affective computing literature -Gaussian Mixture Models (GMM), Support Vector Machines (SVM) and Multilayer Perceptron neural networks (MLP) -as well as the recently proposed Hierarchical Fuzzy Signature (HFS) classifier. Among these, a hybrid classifier using GMM models and SVM gave the best overall classification results. Comparing feature, score, and decision fusion, score fusion performed better for GMM, HFS and MLP, while decision fusion worked best for SVM (both for raw data and GMM models). Feature fusion performed worse than other fusion methods in this study. We found that loudness, root mean square, and intensity were the voice features that performed best to detect depression in this dataset.

View PDFchevron_right
Depression Detection Through Speech Analysis : A Survey
International Journal of Scientific Research in Computer Science, Engineering and Information Technology IJSRCSEIT

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2019

Depression is a common and serious medical illness which affects the way how we think, feel and act. Although harmless in its initial stages, it can cause serious problems if detected at a later stage. Due to advancements in technology, it is now possible to detect signs of depression. Different implementation of machine learning algorithms has been worked upon to detect factors causing depression. It is found that speech of a person is dramatically affected and various vocal features are used to classify depression.

View PDFchevron_right
Language independent detection possibilities of depression by speech
Vicsi Klára, David Sztahó, miklós gábriel tulics

In this study acoustic-phonetic analysis of continuous speech, and statistical analyses were performed in order to find parameters in depressed speech that show significant differences compared to a healthy reference group. Read speech materials were gathered in the Hun-garian and Italian languages from both healthy people and patients diagnosed with different degrees of depression. By statistical examination it was found that there are many parameters in the speech of depressed people that show significant differences compared to a healthy reference group. Moreover most of those parameters behave similarly in other languages such as in Italian language. For classification of the healthy and depressed speech, these parameters were used as an input for the classifiers. Two classification methods were compared: Support Vector Machine (SVM) and a two-layer feed-forward neural network (NN). No difference was found between the result of the two methods when trained and tested on Hungarian language (both SVM and NN classification accuracy was 75%). In case of training with Hungarian and testing with Italian healthy and depressed speech both classifier reached 77% of accuracy.

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved