My Profile

My Photo
He graduated from the Dept. of Mathematics of the Aristotle University of Thessaloniki in 2001. He continued his studies at the School of Medicine of the same University until 2003, where he obtained the M.Sc. in Medical Informatics. In 2008, he obtained the Ph.D. in Informatics entitled as "Digital Processing Techniques in Speech Emotion Recognition" at the Computer Science faculty of the same University. He served in the Army during 2008-2009. He has been awarded the ERCIM fellowship for 2009-2011. In 2009, he was with VTT Technical Research Center of Finland working on Alzeimer's disease and Neurally Adjusted Ventilation Assist (NAVA). In 2010-2011, he was with IAIS Fraunhofer Institute in Bonn working on Speech Analysis. He is currently a researcher in CERTH, Centre for Research and Technology Hellas working on Augmented Reality for Android devices.

FastAR: An Augmented Reality component for Joomla/Sobipro supporting Junaio, Layar, and Wikitude AR browsers

FastAR lets you exploit open tools, i.e. Sobipro in a Joomla framework, and commercial tools such as the three major augmented reality browsers, namely Junaio, Layar, Wikitude to make Augmented Reality without any code writting! Free to download [here]


Improve My City Mobile

ImproveMyCity-Mobile is the Android counterpart of the IMC Joomla component to report, vote and track non-emergency issues [Conf. Pub. 17]. The application enables citizens to report local problems such as potholes, illegal trash dumping, faulty street lights, broken tiles on sidewalks, and illegal advertising boards. Source code for mobile available at github

Neurally adjusted ventilation assist for critically ill patients

Neurally adjusted ventilatory assist (NAVA) delivers airway pressure (P_aw) in proportion to the electrical activity of the diaphragm (EAdi) using an adjustable proportionality constant (NAVA level, cm H_20/microvolt). During systematic increases in the NAVA level, feedback-controlled down-regulation of the EAdi results in a characteristic two-phased response in P_aw and tidal volume (Vt). The transition from the 1st to the 2nd response phase allows identification of adequate unloading of the respiratory muscles with NAVA (NAVA_AL). We aimed to develop and validate a mathematical algorithm to identify NAVA_AL. More details can be found in published journal manuscript 7 [pdf].

Signals like airway pressure and electrical activity of the diaphragm are recorded.

Software developed in Matlab for the automatic estimation of NAVA adequate level.

The methodology presented graphically.

HearAmpFFT - Android app

Signal Processing applications
  • Sound Amplification for Hearing impaired or Electrical Guitar
  • Guitar tuning
  • Spectrum view up to 22 kHz

Whistle2Piano for Symbian Mobile Phones using Python for S60

A tool to convert human whistling sounds to piano notes by employing the spectrogram of the sound. Notes can be exported to Music xml format for further processing [pdf]. Implemented for Symbian 60 3rd Edition FP2 using python language.

The Vocal Tract LaTeX package

VocalTract.sty is a Latex package to visualize the vocal tract. Further information can be found in journal paper [8]. The package can be downloaded from [CTAN].  VTCalcs users: In order to install my software as a plug-in download also the update version of arcb.m


Information loss of the Mahalanobis distance in high dimensions: Matlab implementation

The information loss is estimated and exploited to set a lower limit for the correct classification rate achieved by the Bayes classifier that is used in subset feature selection. Details of the method can be found in journal paper [6]. The functions to estimate the lower limit of correct classification rate (CCR) can be downloaded from Matlab File Exchange.

Speaker Segmentation Demo for Matlab

The target of the software is to divide speech into 3 classes: Silence, Male, Female. In Stage 1, speech is classified into voiced or unvoiced frames by applying Gabor filtering and energy tracking by a method of G. Evangelopoulos. In Stage 2, it is assumed that if two speakers exist, then they would have significant different fundamental frequency and energy below 150 Hz regions, i.e. one actor would tend to be bass and the other will tend to be soprano, these differences are tracked again with the GMM algorithm. This method can be found in [5] at Journal Publications Section.

Feature Selection for Python and Matlab

Feature selection algorithms with graphical user interface for loading a pattern x features matrix and selecting the subset of features that maximizes correct classification rate. The proposed Sequential Forward Selection (SFS) employs preliminary rejections and tentative cross-validation repetittions, to improve the speed and the accuracy of SFS, respectively. Further information can be found in journal paper [4] and conference announcement [15]. A demo version can be downloaded from Download from Matlab file exchage site.


Gaussian Mixture Modeling for Matlab

The Expectation-Maximization algorithm (EM) is widely used to find the parameters of a mixture of Gaussian probability density functions (pdfs) or briefly Gaussian components that fits the sample measurement vectors in maximum likelihood sense. In our work, the expectation-maximization (EM) algorithm for Gaussian mixture modeling is improved via three statistical tests: a) A multivariate normality test, b) a central tendency (kurtosis) criterion, and c) a test based on marginal cdf to find a discriminant to split a non-Gaussian component. Details of the method can be found in journal paper [3]. The method can be downloaded from: Download from Matlab file exchange.


Solar car with LEGO parts

Small scale car development using LEGO parts. A 50 cm length solar car that stores the energy in Ni-Mh batteries. The car can be either remote controled or machine controled using the NXT brick processor. Project site

Ph.D. dissertation

Digital Speech Processing Techniques for Emotion Recognition ([pdf], Greek)
Supervisor: Associate Professor Constantine Kotropoulos
Artificial Intelligence and Information Analysis Laboratory, Dept. Informatics Aristotle Univ. of Thessaloniki (AUTH)

Journal Publications

1. Dimitrios Ververidis and Constantine Kotropoulos, "Emotional speech recognition: Resources, features, methods, and applications," Elsevier Speech Communication, vol. 48, issue 9, pp. 1162-1181, Sep. 2006. [pdf]

2. Vassiliki Moschou, Dimitrios Ververidis, Constantine Kotropoulos, "Assessment of self organizing map variants for clustering with application to redistribution of emotional speech patterns," Elsevier Neurocomputing, vol. 71, issues 1-3, pp. 147-156, 2007. [pdf]

3. Dimitrios Ververidis and Constantine Kotropoulos, "Gaussian mixture modeling by exploiting the Mahalanobis distance," IEEE Trans. Signal Processing, vol. 56, issue 7B, pp. 2797-2811, 2008. [pdf]

4. Dimitrios Ververidis and Constantine Kotropoulos, "Fast and accurate feature subset selection applied into speech emotion recognition," Elsevier Signal Processing, vol. 88, issue 12, pp. 2956-2970, 2008. [pdf]

5. M. Kotti, D. Ververidis, G. Evangelopoulos, I. Panagakis, C. Kotropoulos, P. Maragos, and I. Pitas, "Audio-assisted movie dialogue detection," IEEE Trans. Circuits and Systems for Video Technology, vol. 18, issue 11, pp. 1618-1627, 2008. [pdf]

6. Dimitrios Ververidis and Constantine Kotropoulos, "Information loss of the Mahalanobis distance in high dimensions: Application to feature selection," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31, no. 12, pp. 2275-2281, 2009. [pdf]

7. Dimitrios Ververidis, Mark Van Gils, Christina Passath, Jukka Takala and Lukas Brander, "Identification of adequate neurally adjusted ventilatory assist (NAVA) during systematic increases in the NAVA level," IEEE Trans. Biomedical Engineering, vol. 58, no. 9, pp. 2598-2606, Sept. 2011. [pdf]

8. Dimitrios Ververidis, Daniel Schneider, and Joachim Koehler, "The vocal tract LaTeX package," PracTeX journal, no 1, 2012 [pdf]. Package available at CTAN.

Conference Announcements

1. D. Ververidis and C. Kotropoulos, "A Review of Emotional Speech Databases," in Proc. 9th Panhellenic Conference on informatics (PCI), pp. 560-574, Thessaloniki, Greece, November 2003. [pdf]

2. D. Ververidis and C. Kotropoulos, "A State of the Art Review on Emotional Speech Databases," in Proc. 1st Richmedia Conference, pp. 109-119, Laussane, Oktober 2003. [pdf]

3. D. Ververidis, C. Kotropoulos and I. Pitas, "Automatic Emotional Speech Classification," in Proc. Int. Conf. Acoustics Speech and Signal Processing (ICASSP), vol. 1, pp. 593-596, Montreal, Canada, 2004. [pdf]

4. D. Ververidis and C. Kotropoulos, "Automatic Speech Classification to Five Emotional States Based on Gender Information," in Proc. European Signal Processing Conference (EUSIPCO), pp. 341–344, Austria, 2004. [pdf]

5. D. Ververidis and C. Kotropoulos, "Emotional speech classification using Gaussian mixture models," in Proc. IEEE Inter. Symposium on Circuits and Systems (ISCAS), Japan, 2005. [pdf]

6. D. Ververidis and C. Kotropoulos, "Emotional speech classification using Gaussian mixture models and the Sequential Floating Forward Selection algorithm," in Proc. IEEE Int. Conf. on Multimedia & Expo. (ICME), Amsterdam, 2005. [pdf]

7. D. Ververidis and C. Kotropoulos, "Sequential forward feature selection with low computational cost," in Proc. European Signal Processing Conference (EUSIPCO), Antalya, Turkey, 2005. [pdf]

8. D. Ververidis and C. Kotropoulos, "Fast Sequential Floating Forward Selection applied to emotional speech features estimated on DES and SUSAS data collections," in Proc. European Signal Processing Conf. (EUSIPCO), Italy, 2006. [pdf]

9. M. Haindl, P. Somol, D. Ververidis, and C. Kotropoulos, "Feature Selection Based on Mutual Correlation," in Proc. 11th Iberoamerican Congress on Pattern Recognition (CIAPR), Mexico, 2006. [pdf]

10. V. Moschou, D. Ververidis and C. Kotropoulos, "On the variants of the self-organizing map that are based on order statistics," in Proc. Inter. Conf. Artificial Neural Networks (ICANN), Athens, Sep. 2006. [pdf]

11. M. Sedaaghi, D. Ververidis and C. Kotropoulos, "Improving speech emotion recognition using adaptive genetic algorithms," in Proc. European Signal Processing Conference (EUSIPCO), Polland, 2007. [pdf]

12. D. Ververidis and C. Kotropoulos, "Accurate estimate of the cross-validated prediction error variance in Bayes classifiers," in Proc. Machine Learning for Signal Processing (MLSP), Thessaloniki, 2007. [pdf]

13. M. Sedaaghi, C. Kotropoulos, and D. Ververidis, "Using adaptive genetic algorithms to improve speech emotion recognition," in Proc. IEEE Workshop Multimedia Signal Processing (MMSP), Crete, 2007. [pdf]

14. D. Ververidis, I. Kotsia, C. Kotropoulos, and Ioannis Pitas, "Multi-modal emotion-related data collection within a virtual earthquake emulator," in Proc. Inter. Conf. Language Resources and Evaluation (LREC), Morocco, 2008. [pdf]

15. D. Ververidis, M. Van Gils, J. Koikkalainen, and J. Lotjonen, "Feature selection and time regression software: Application on predicting Alzheimer's disease progress," in Proc. European Signal Processing Conference (EUSIPCO), Aalborg, 2010. [pdf]

16. J. Mattila, H. Soininen, D. Ververidis, M. van Gils, J. Lotjonen, G. Waldemar, A. H. Simonsen, D. Rueckert, L. Thurfjell, and J. Koikkalainen, "Clinical decision support system based on statistical analysis of heterogeneous clinical data and Alzheimer biomarkers," in Proc. Intern. Conf. Alzheimer's Disease (ICAD), Hawaii, 2010.

17. I. Tsampoulatidis, D. Ververidis, P. Tsarchopoulos, S. Nikolopoulos, I. Kompatsiaris, N. Komninos, "ImproveMyCity – An open source platform for direct citizen-government communication," in Proc. ACM Intern. Conf. Multimedia, 2013. [pdf]

18. D. Ververidis, S. Nikolopoulos, and I. Kompatsiaris, "Transforming your website to an Augmented Reality view," in Proc. IEEE Intern. Symp. on Mixed and Augmented Reality (ISMAR), Fukuoka, 2015. [pdf]