Advertisement

Noise Subspace Fuzzy C-Means Clustering for Robust Speech Recognition

  • J. M. Górriz
  • J. Ramírez
  • J. C. Segura
  • C. G. Puntonet
  • J. J. González
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3984)

Abstract

In this paper a fuzzy C-means (FCM) based approach for speech/non-speech discrimination is developed to build an effective voice activity detection (VAD) algorithm. The proposed VAD method is based on a soft-decision clustering approach built over a ratio of subband energies that improves recognition performance in noisy environments. The accuracy of the FCM-VAD algorithm lies in the use of a decision function defined over a multiple-observation (MO) window of averaged subband energy ratio and the modeling of noise subspace into fuzzy prototypes. In addition, time efficiency is also reached due to the clustering approach which is fundamental in VAD real time applications, i.e. speech recognition. An exhaustive analysis on the Spanish SpeechDat-Car databases is conducted in order to assess the performance of the proposed method and to compare it to existing standard VAD methods. The results show improvements in detection accuracy over standard VADs and a representative set of recently reported VAD algorithms.

Keywords

Speech Recognition Discrete Fourier Transform Speech Recognition System Voice Activity Detection IEEE Signal Processing Letter 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    ETSI, Voice Activity Detector (VAD) for Adaptive Multi-Rate (AMR) Speech Traffic Channels, ETSI EN 301 708 Recommendation (1999)Google Scholar
  2. 2.
    ITU, A silence compression scheme for G.729 optimized for terminals conforming to recommendation v. 70, ITU-T Recommendation G.729-Annex B (1996)Google Scholar
  3. 3.
    Sohn, J., Kim, N.S., Sung, W.: A statistical model-based voice activity detection. IEEE Signal Processing Letters 16(1), 1–3 (1999)CrossRefGoogle Scholar
  4. 4.
    Bouquin-Jeannes, R.L., Faucon, G.: Study of a voice activity detector and its influence on a noise reduction system. Speech Communication 16, 245–254 (1995)CrossRefGoogle Scholar
  5. 5.
    Woo, K., Yang, T., Park, K., Lee, C.: Robust voice activity detection algorithm for estimating noise spectrum. Electronics Letters 36(2), 180–181 (2000)CrossRefGoogle Scholar
  6. 6.
    Li, Q., Zheng, J., Tsai, A., Zhou, Q.: Robust endpoint detection and energy normalization for real-time speech and speaker recognition. IEEE Transactions on Speech and Audio Processing 10(3), 146–157 (2002)CrossRefGoogle Scholar
  7. 7.
    Marzinzik, M., Kollmeier, B.: Speech pause detection for noise spectrum estimation by tracking power envelope dynamics. IEEE Transactions on Speech and Audio Processing 10(6), 341–351 (2002)CrossRefGoogle Scholar
  8. 8.
    Ramírez, J., Segura, J.C., Benítez, C., García, L., Rubio, A.: Statistical Voice Activity Detection using a Multiple Observation Likelihood Ratio Test. IEEE Signal Processing Letters 12(10), 689–692 (2005)CrossRefGoogle Scholar
  9. 9.
    Anderberg, M.R.: Cluster Analysis for Applications. Academic Press, Inc., New York (1973)MATHGoogle Scholar
  10. 10.
    Rasmussen, E.: Clustering algorithms. In: Frakes, W.B., Baeza-Yates, R. (eds.) Information Retrieval: Data Structures and Algorithms, pp. 419–442. Prentice-Hall, Inc., Upper Saddle River (1992)Google Scholar
  11. 11.
    Jain, A.K., Dubes, R.C.: Algorithms for Clustering Data. Prentice-Hall advanced reference series. Prentice-Hall, Inc., Upper Saddle River (1988)Google Scholar
  12. 12.
    Ramírez, J., Segura, J.C., Benítez, C., de la Torre A., Rubio, A.: An Effective Subband OSF-based VAD with Noise Reduction for Robust Speech Recognition. IEEE Trans. on Speech and Audio Processing (2005) (in press)Google Scholar
  13. 13.
    Dunn, J.: A fuzzy relative of the ISODATA process and its use in detecting compact well separated clusters. J. Cybern. 3(3), 32–57 (1974)CrossRefMathSciNetGoogle Scholar
  14. 14.
    Bezdek, J.: Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum, New York (1981)MATHGoogle Scholar
  15. 15.
    Moreno, A., Borge, L., Christoph, D., Gael, R., Khalid, C., Stephan, E., Jeffrey, A.: SpeechDat-Car: A Large Speech Database for Automotive Environments. In: Proceedings of the II LREC Conference (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • J. M. Górriz
    • 1
  • J. Ramírez
    • 1
  • J. C. Segura
    • 1
  • C. G. Puntonet
    • 2
  • J. J. González
    • 2
  1. 1.Dpt. Signal Theory, Networking and communicationsUniversity of GranadaSpain
  2. 2.Dpt. Computer Architecture and TechnologyUniversity of GranadaSpain

Personalised recommendations