Advertisement

Beam-Search Formant Tracking Algorithm Based on Trajectory Functions for Continuous Speech

  • José Enrique García Laínez
  • Dayana Ribas González
  • Antonio Miguel Artiaga
  • Eduardo Lleida Solano
  • José Ramón Calvo de Lara
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7441)

Abstract

This paper presents a formant frequency tracking algorithm for continuous speech processing. First, it uses spectral information for generating frequency candidates. For this purpose, the roots of the polynomial of a Linear Predictive Coding (LPC) and peak picking of Chirp Group Delay Function (CGD) were tested. The second stage is a beam-search algorithm that tries to find the best sequence of formants given the frequency candidates, applying a cost function based on local and global evidences. The main advantage of this beam-search algorithm compared with previous dynamic programming approaches lies in that a trajectory function that takes into account several frames can be optimally incorporated to the cost function. The performance was evaluated using a labeled formant database and the Wavesurfer formant tracker, achieving promising results.

Keywords

formant tracking chirp group delay beam-search algorithm speech processing 

References

  1. 1.
    Rose, P.: Forensic Speaker Identification. In: Robertson, J. (ed.) Taylor and Francis Forensic Science Series. Taylor and Francis, London (2002)Google Scholar
  2. 2.
    McCandless, S.: An algorithm for automatic formant extraction using linear prediction spectra. IEEE TASSP ASSP-22, 135–141 (1974)CrossRefGoogle Scholar
  3. 3.
    Yegnanarayana: Formant extraction from linear prediction phase spectrum. Journal of Acoustic Society of America 63, 1638–1640 (1978)CrossRefGoogle Scholar
  4. 4.
    Bozkurt, B., Couvreur, L., Dutoit, T.: Chirp group delay analysis of speech signals. Speech Communications (2007)Google Scholar
  5. 5.
    Mehta, D.D., Rudoy, D., Wolfe, P.J.: KARMA: Kalman-based autoregressive moving average modeling and inference for formant and antiformant tracking. stat. AP (2011)Google Scholar
  6. 6.
    Gläser, C., Heckmann, M., Joublin, F., Goerick, C.: Combining auditory preprocessing and Bayesian Estimation for Robust Formant Tracking. IEEE Trans. Audio Speech Lang. Process. (2010)Google Scholar
  7. 7.
    Messaoud, Z.B., Gargouri, D., Zribi, S., Hamida, A.B.: Formant Tracking Linear Prediction Model using HMMs for Noisy Speech Processing. Int. Journal of Inf. and Comm. Eng. 5(4) (2009)Google Scholar
  8. 8.
    Talkin, D.: Speech formant trajectory estimation using dynamic programming with modulated transition costs. JASA 82(S1), 55 (1987)Google Scholar
  9. 9.
    Deng, L., Bazzi, I., Acero, A.: Tracking Vocal Tract Resonances Using an Analytical Nonlinear Predictor and a Target-Guided Temporal Constraint (2003)Google Scholar
  10. 10.
    Xia, K., Espy-Wilson, C.: A new strategy of formant tracking based on dynamic programming. In: Proc. ICSLP (2000)Google Scholar
  11. 11.
    Rabiner, L.R., Shafer, R.W.: The Chirp z-Transform Algorithm. IEEE Transactions on Audio and Electroacoustics au-17(2) (1969)Google Scholar
  12. 12.
    Garcia, J.E., Ortega, A., Miguel, A., Lleida, E.: Predictive vector quantization using the M-algorithm for distributed speech recognition. In: FALA (2010)Google Scholar
  13. 13.
    Jelinek, F., Anderson, J.B.: Instrumentable Tree Encoding of Information Sources. IEEE Trans. on Information Theory, 118–119 (1971)Google Scholar
  14. 14.
    Deng, L., Cui, X., Pruvenok, R., Huang, J., Momen, S., Chen, Y., Alwan, A.: A Database of Vocal Tract Resonance Trajectories for Research in Speech Processing. In: ICASSP (2006)Google Scholar
  15. 15.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • José Enrique García Laínez
    • 1
  • Dayana Ribas González
    • 2
  • Antonio Miguel Artiaga
    • 1
  • Eduardo Lleida Solano
    • 1
  • José Ramón Calvo de Lara
    • 2
  1. 1.Communications Technology Group (GTC), Aragon Institute for Engineering Research (I3A)University of ZaragozaSpain
  2. 2.Advanced Technologies Application Center (CENATAV)La HabanaCuba

Personalised recommendations