Classification of Fricatives Using Novel Modulation Spectrogram Based Features

  • Kewal D. Malde
  • Anshu Chittora
  • Hemant A. Patil
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8251)


In this paper, we propose the use of a novel feature set, i.e., modulation spectrogram for fricative classification. Modulation spectrogram gives 2-dimensional (i.e., 2-D) feature vector for each phoneme. Higher Order Singular Value Decomposition (HOSVD) is used to reduce the size of large dimensional feature vector obtained by modulation spectrogram. These features are then used to classify the fricatives in five broad classes on the basis of place of articulation (viz., labiodental, dental, alveolar, post-alveolar and glottal). Four-fold cross-validation experiments have been conducted on TIMIT database. Our experimental results show 89.09 % and 87.51 % accuracies for recognition of place of articulation of fricatives and phoneme-level fricative classification,respectively, using 3-nearest neighbor classifier.


Fricative classification modulation spectrogram HOSVD place of articulation acoustic frequency and modulation frequency 


  1. 1.
    Quatieri, T.F.: Discrete-time Speech Signal Processing: Principles and Practice. Prentice Hall Press, Upper Saddle River (2004)Google Scholar
  2. 2.
    Web Source, (last accessed on 30th April, 2013)
  3. 3.
    Garofolo, J.S.: Getting started with the DARPA TIMIT CD-ROM: An acoustic phonetic continuous speech database. National Institute of Standards and Technology (NIST), Gaithersburgh, MD (1988)Google Scholar
  4. 4.
    Scanlon, P., Ellis, D., Reilly, R.: Using Broad Phonetic Group Experts for Improved Speech Recognition. IEEE Trans. on Audio, Speech and Language Proc. 15, 803–812 (2007)CrossRefGoogle Scholar
  5. 5.
    Ali, A.M.A., Spiegel, J.V., Mueller, P.: Acoustic-phonetic features for automatic classification of fricatives. J. Accoust. Soc. of America 109(5), 2217–2235 (2001)CrossRefGoogle Scholar
  6. 6.
    Ali, A.M.A., Spiegel, J.V., Muller, P.: An acoustic-phonetic feature-based system for the automatic recognition of fricative consonents. In: IEEE Proc. on Int. Conf. on Acoustics, Speech and Signal Processing, vol. 2, pp. 961–964 (1998)Google Scholar
  7. 7.
    Seneff, S.: A Joint Synchrony/ Mean Rate Model of Auditory Speech Processing. J. Phonetics 16, 55–76 (1988)Google Scholar
  8. 8.
    Atlas, L., Shamma, A.S.: Joint acoustic and modulation frequency. EURASIP J. on Applied signal Proccessing 7, 668–675 (2003)CrossRefGoogle Scholar
  9. 9.
    Greenberg, S., Kingsbury, B.: The modulation spectrogram: In pursuit of an invariant representation of speech. In: IEEE Proc. on Int. Conf. on Acoust., Speech, Signal Process., Munich, Germany, vol. 3, pp. 1647–1650 (1997)Google Scholar
  10. 10.
    Markaki, M., Stylianou, Y.: Voice pathology detection and discrimination based on modulation spectral features. IEEE Trans. on Audio, Speech, and Language Proc. 19(7), 1938–1948 (2011)CrossRefGoogle Scholar
  11. 11.
    Lathauwer, L.D., Moor, B.D., Vandewalle, J.: A multilinear singular value decomposition. SIAM J. Matrix Anal. Appl. 21(4), 1253–1278 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Modulation Toolbox, (last accessed on 30th April 2013)

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Kewal D. Malde
    • 1
  • Anshu Chittora
    • 1
  • Hemant A. Patil
    • 1
  1. 1.Dhirubhai Ambani Institute of Information and Communication TechnologyGandhinagarIndia

Personalised recommendations