Open access


The paper describes our experiment with using the Gaussian mixture models (GMM) for classification of speech uttered by a person wearing orthodontic appliances. For the GMM classification, the input feature vectors comprise the basic and the complementary spectral properties as well as the supra-segmental parameters. Dependence of classification correctness on the number of the parameters in the input feature vector and on the computation complexity is also evaluated. In addition, an influence of the initial setting of the parameters for GMM training process was analyzed. Obtained recognition results are compared visually in the form of graphs as well as numerically in the form of tables and confusion matrices for tested sentences uttered using three configurations of orthodontic appliances.

[1] HILTON, L. : Orthodontic Appliances Information on Health- line, Gale Encyclopedia of Nursing and Allied Health, The Gale Group Inc., Gale, Detroit, 2002.

[2] HOHOFF, A.-SEIFERT, E.-FILLION, D.-STAMM, T.- HEINECKE, A.-EHMER, U. : American Journal of Orthodon- tics and Dentofacial Orthopedics 123 (2003), 146-152.

[3] KONG, H. J.-HANSEN, C. A. : Customizing Palatal Contours of a Denture to Improve Speech Intelligibility, The Journal of Prosthetic Dentistry 99 (2008), 243-248.

[4] LANE, H.-DENNY, M.-GUENTHER, F. H.-MATTHIES, M. L.-M´ENARD, L.-PERKELL, J. S.-STOCKMANN, E. -TIEDE, M.-VICK, J.-ZANDIPOUR, M. : Effects of Bite Blocks and Hearing Status on Vowel Production, Journal of Acoustical Society of America 118 No. 3 (2005), 1636-1646.

[5] PŘIBIL, J.-PŘIBILOV´A, A. : An Experiment with Evaluation of Emotional Speech Conversion by Spectrograms, Measurement Science Review 10 No. 3 (2010), 72-77.

[6] PŘIBIL, J.-PŘIBILOV´A, A.-ˇDURAˇCKOV´A, D. : An Ex- periment with Spectral Analysis of Emotional Speech Affected by Orthodontic Appliances, Journal of Electrical Engineering 63 No. 5 (2012), 296-302.

[7] VICH, R. : Cepstral Speech Model, Pad´e Approximation, Ex- citation, and Gain Matching in Cepstral Speech Synthesis, In Proceedings of the 15th Biennial EURASIP Conference Biosig- nal 2000, Brno, Czech Republic, 2000, pp. 77-82.

[8] HOSSEINZADEH, D. KRISHNAN, S. : On the Use of Comple- mentary Spectral Features for Speaker Recognition, EURASIP Journal on Advances in Signal Processing (2008), Article ID 258184.

[9] VEPREK, P.-SCORDILIS, M. S. : Analysis, Enhancement and Evaluation of Five Pitch Determination Techniques, Speech Communication 37 (2002), 249-270.

[10] KOOLAGUDI, S. G.-KROTHAPALLI, R. S. : Two Stage Emotion Recognition Based on Speaking Rate, International Journal of Speech Technology 14 (2011), 35-48.

[11] SHAH, N. H. : Numerical Methods with C++ Programming, Prentice-Hall of India Learning Private Limited, New Delhi, 2009.

[12] REYNOLDS, D. A. : Speaker Identification and Verification us- ing Gaussian Mixture Speaker Models, Speech Communication 17 (1995), 91-108.

[13] MOON, T. K. : IEEE Signal Processing Magazine (Nov 1996), 47-60.

[14] VICH, R.-NOUZA, J.-VONDRA, M. : Automatic Speech Recognition used for Intelligibility Assessment ofText-to-Speech Systems, In Verbal and Nonverbal Features of Human-Human and Human-Machine Interactions (Esposito A., Bourbakis N., Avouris N., Hatrzilygeroudis I., eds.), LNAI vol. 5042, Springer- Verlag Berlin Heidelberg, 2008, pp. 136-148.

[15] REYNOLDS, D. A.-ROSE, R. C. : Robust Text-Independent Speaker Identification Using Gaussian Mixture Speaker Models, IEEE Transactions on Speech and Audio Processing 3 (1995), 72-83.

[16] NABNEY, I. T. : Netlab Pattern Analysis Toolbox, c 1996 -2001, Retrieved 16 February 2012 from http:// www.mathworks.com/matlabcentral/fileexchange/2654-netlab.

Journal of Electrical Engineering

The Journal of Slovak University of Technology

Journal Information

IMPACT FACTOR 2018: 0.636
5-year IMPACT FACTOR: 0.663

CiteScore 2018: 0.88

SCImago Journal Rank (SJR) 2018: 0.200
Source Normalized Impact per Paper (SNIP) 2018: 0.771


All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 227 138 13
PDF Downloads 91 67 10