Abstract
Speech is an integral part of the human communication system. Various pathological conditions affect the vocal functions, inducing speech disorders. Acoustic parameters of speech are commonly used for the assessment of speech disorders and for monitoring the progress of the patient over the course of therapy. In the last two decades, signal-processing techniques have been successfully applied in screening speech disorders. In the paper, a novel approach is proposed to classify pathological speech signals using a local discriminant bases (LDB) algorithm and wavelet packet decompositions. The focus of the paper was to demonstrate the significance of identifying the signal subspaces that contribute to the discriminatory characteristics of normal and pathological speech signals in a computationally efficient way. Features were extracted from target subspaces for classification, and time-frequency decomposition was used to eliminate the need for segmentation of the speech signals. The technique was tested with a database of 212 speech signals (51 normal and 161 pathological) using the Daubechies wavelet (db4). Classification accuracies up to 96% were achieved for a two-group classification as normal and pathological speech signals, and 74% was achieved for a four-group classification as male normal, female normal, male pathological and female pathological signals.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Agbinya, J. I. (1996): ‘Discrete wavelet transform techniques in speech processing’Proc. IEEE TENCON, Digital Signal Processing Applications,2, pp. 514–519
Athineos, M., andEllis, D. P. W. (2003): ‘Frequency-domain linear prediction for temporal features’.Proc. IEEE Workshop on Automatic Speech Recognition & Understanding, ASRU '03, pp. 261–266
Baken, R. J., andOrlikoff, R. F. (2000): ‘Clinical measurement of speech and voice’ (Singular Publications, SanDiego, CA, 2000)
Christian, B. (2002): ‘Local discriminant bases and optimized wavelet to classify ultrasonic echoes: application to indoor mobile robotics’,Proc. IEEE, Sensors,2, pp. 1654–1659
Coifman, R. R., andWickerhauser, M. V. (1992): ‘Entropy-based algorithms for best basis selection’,IEEE Trans. Inform. Theory,38, pp. 713–718
Database (1994): ‘Voice disorders database, version 1.03 (CDROM)’. Massachusetts Eye & Ear Infirmary,Kay Elemetrics Corporation, Lincoln Park, NJ, USA
Eskenazi, L., Childers, D. G., andHicks, D. M. (1990): ‘Acoustics correlates of vocal quality’,J. Speech Hearing Res.,33, pp. 298–306
Fukunaga, K. (1990): ‘Introduction to statistical pattern recognition’ (Academic Press, Inc., San Diego, CA, 1990)
Godino-Llorente, J. I., andGomez-Vilda, P. (2004): ‘Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors’,IEEE Trans. Biomed. Eng.,51, pp. 380–384
Hammarberg, B. (1980): ‘Perceptual and acoustic correlates of abnormal voice qualities’,Acta Otolaryngol. 90, pp. 441–451
Hermansky, H., Tsuga, K., Makino, S., andWakita, H. (1986): Perceptually based processing in automatic speech recognition. InProc. of the International Conference on Acoustics, Speech, and Signal Processing ICASSP '86. pp. 1971–1974
Hillman, R. E., Qui, Y., andMilstein, C. (1999): ‘The estimation of signal-to-noise ratio in continuous speech for disordered voices’,J. Acoust. Soc. Am.,105, pp. 2532–2535
Hsieh, C. T., Lai, E., andWang, Y. C. (2002): ‘Robust speech features based on wavelet transform with application to speaker identification’,IEE Proc. Vis. Image Signal Process.,149, pp. 108–114
Juang, B. H., andChen, T. (1998): ‘The past, present and future of speech processing’,IEEE Signal Process. Mag.,15, pp. 28–48
Kadambe, S., andSrinivasan, P. (1994): ‘Application of adaptive wavelets for speech coding’.Proc. IEEE-SP Int. Symposium on Time-frequency and Time-scale analysis, pp. 632–635
Klingholz, F. (1990): ‘Acoustic recognition of voice disorders: A comparative study, running speech versus sustained vowels’,J. Acoust. Soc. Am.,87, pp. 2218–2224
Krishnan, S., Rangayyan, R. M., Bell, G. D., Frank, C. B., andLadly, K. O. (1996): ‘Screening of knee joint vibroarthrographic signals by statistical pattern analysis of dominant poles’.Proc. Int. Conf. on Engineering in Medicine & Biology-Bridging Disciplines for Biomedicine, pp. 968–969
Long, C. J., andDatta, S. (1996): ‘Wavelet based feature extraction for phoneme recognition’.Proc. Fourth Int. Conf. on Spoken Language, ICSLP, pp. 264–267
Lukasik, E. (2000): ‘Wavelet packets based feature selection for voiceless plosives classification’.Proc. Int. Conf. on Acoustics, Speech, & Signal Processing, ICASSP-2000, pp. II689–II692
Mallat, S. G., andZhang, Z. (1993): ‘Matching pursuit with time-frequency dictionaries’,IEEE Trans. Signal Process.,41, 3397–3415
Mallat, S. (1998): ‘A wavelet tour of signal processing’ (Academic Press, San Diego, CA, 1998)
Najih, A. M. M. A., Ramli BIN, A. R., Prakash, V., andSyed, A. R. (2003): ‘Speech compression using discrete wavelet transform’.Proc. 4th National Conf. on Telecommunication Technology, pp. 1–4
Parsa, V., andJamieson, D. G. (2000): ‘Identification of pathological voices based on glottal noise measures’,J. Speech Hearing Res.,43, pp. 469–485
Parsa, V., andJamieson, D. G. (2001): ‘Acoustic discrimination of pathological voice: Sustained vowels versus continuous speech’.J. Speech, Lang. Hearing Res.,44, pp. 327–339
Picone, J. W. (1993): ‘Signal modelling techniques in speech recognition’.Proc. IEEE Trans.,81, pp. 1215–1247
Ris, C., Fontaine, V., andLeich, H. (1995): ‘Speech analysis based on Malvar wavelet transform’.Proc. Int. Conf. Acoustics, Speech & Signal Processing ICASSP-95, pp. 389–392
Saito, N., &Coifman, R. R., (1995): ‘Local discriminant bases and their applications’,J. Math. Imag. Vis. 5, pp. 337–358
Spooner, C. M. (2001): ‘Application of local discriminant bases to HRR-based ATR’.Proc. Signals, Systems & Computers, 35th Asilomar Conf., pp. 1067–1073
Spss (1990): SPSS advanced statistics users guide, in ‘User manual’, (SPSS Inc., Chicago, IL, 1990)
Suleesathira, R., andChaparro, L. F. (1998): ‘Evolutionary spectral analysis using Malvar wavelet transform’.Proc. Int. Symposium on Time-frequency & Time-scale analysis, IEEE SP, pp. 673–676
Tzanetakis, G., andCook, P. (2002): ‘Musical genre classification of audio signals’,IEEE Trans. Speech Audio Process.,10 pp. 293–302
Umapathy, K., Krishnan, S., Parsa, V., andJamieson, D. G. (2002): ‘Time-frequency modeling and classification of pathological voices’.Proc. IEEE Engineering in Medicine & Biology Society (EMBS) 2002 Conf., Houston, Texas, USA, pp. 116–117
Umapathy, K., andKrishnan, S. (2004): ‘Modified local discriminant bases and its applications in signal classification’,Proc. Int. Conf. on Acoustics, Speech & Signal Processing 2004 ICASSP 2004,2, pp. 745–748
Veselinovic, D. andGraupe, D. (2003): ‘A wavelet transform approach to blind adaptive filtering of speech from unknown noises’,IEEE Trans. Circuits Syst. II, Analog Digit. Signal Process.50, pp. 150–154
Web, A. (2002):Statistical pattern recognition, (Wiley, West Sussex, England, 2002)
Yumato, E., Sasaki, Y., andOkamura, H. (1984): ‘Harmonics-to-noise ratio and psychophysical measurement of the degree of hoarseness’,J. Speech Hearing Res.,27, pp. 2–6
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Umapathy, K., Krishnan, S. Feature analysis of pathological speech signals using local discriminant bases technique. Med. Biol. Eng. Comput. 43, 457–464 (2005). https://doi.org/10.1007/BF02344726
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02344726