Advertisement

SSM – A Novel Method to Recognize the Fundamental Frequency in Voice Signals

  • György VárallyayJr.
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4756)

Abstract

Nowadays the detection of the fundamental frequency (F 0) in voice signals can be evaluated by several algorithms. There are two main attributes of these algorithms: exactness and calculation time. A considerable part of the algorithms are based on the well-known Fast Fourier Transformation (FFT). The Smoothed Spectrum Method is an FFT based process, which was developed for the F 0 detection of recorded voice signals especially the infant cry. As it will be shown the SSM provides a better accuracy than regular FFT based algorithms or the Autocorrelation Function. In case of sound recordings in noisy environment the modified SSM is able to recognize significant noise components in the recorded signal. A further advantage of SSM is that additional information of the analyzed signal can be given to improve the performance of the method.

Keywords

Fundamental frequency detection voice signals noise detection 

References

  1. 1.
    Deller, J.R., Proakis, J.G., Hansen, J.H.L.: Discrete-time processing of speech signals. MacMillan Publishing Co, New York (1993)Google Scholar
  2. 2.
    Parsa, V., Jamieson, D.G.: A Comparison of High Precision F0 Extraction Algorithms for Sustained Vowels. J. of Speech, Language, and Hearing Research 42, 112–126 (1999)Google Scholar
  3. 3.
    Cheveigné, A., Kawahara, H.: YIN, a fundamental frequency estimator for speech and music. J. Acoust. Soc. Am. 111, 1917–1930 (2002)CrossRefGoogle Scholar
  4. 4.
    Randall, R.B.: Application of B&K equipment to frequency analysis. Brüel & Kjaer Techn. Library, Denmark (1977)Google Scholar
  5. 5.
    Barr, R.G., Hopkins, B., Green, J.A.: Crying as a sign, a symptom and a signal. MacKeith Press, London (2000)Google Scholar
  6. 6.
    Hirschberg, J., Szende, T.: Pathological cry, stridor and cough in infants. Akadémiai Kiadó, Budapest (1982)Google Scholar
  7. 7.
    Várallyay Jr., G., Benyó, Z., Illényi, A.: The development of the melody of the infant cry to detect disorders during infancy. In: Proc. IASTED International Conference on Biomedical Engineering (BioMED 2007), Innsbruck, Austria, February 14-16, pp. 186–191 (2007)Google Scholar
  8. 8.
    Möller, S., Schönweiler, R.: Analysis of infant cries for the early detection of hearing impairment. Speech Commun. 28, 175–193 (1999)CrossRefGoogle Scholar
  9. 9.
    Cacace, A.T., Robb, M.P., Saxman, J.H., Risemberg, H., Koltai, P.: Acoustic features of normal-hearing pre-term infant cry. Int. J. Pediatr. Otorhinolaryngol. 33, 213–224 (1995)CrossRefGoogle Scholar
  10. 10.
    Várallyay Jr., G.: Future Prospects of the Application of the Infant Cry in the Medicine. Per. Pol. Elec. Eng. 50, 47–62 (2006)Google Scholar
  11. 11.
    Fort, A., Manfredi, C.: Acoustic analysis of newborn infant cry signals. Med. Eng. Phys. 20, 432–442 (1998)CrossRefGoogle Scholar
  12. 12.
    Michelsson, K., Michelsson, O.: Phonation in the newborn, infant cry. Int. J. Pediatr. Otorhinolaryngol. 301, S297–S301 (1999)CrossRefGoogle Scholar
  13. 13.
    Várallyay Jr., G.: Infant cry analyzer system for hearing disorder detection. Trans. on Automatic Control and Computer Science 49, 57–60 (2004)Google Scholar
  14. 14.
    Wermke, K., Mende, W., Manfredi, C., Bruscaglioni, P.: Developmental aspects of infant’s cry melody and formants. Med. Eng. Phys. 24, 501–514 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • György VárallyayJr.
    • 1
  1. 1.Budapest University of Technology and Economics, Dept. of Control Engineering and Information Technology, Magyar tudósok krt. 2. IB. 311, H-1117 BudapestHungary

Personalised recommendations