Text Independent Speaker Recognition Model Based on Gamma Distribution Using Delta, Shifted Delta Cepstrals

  • K. Suri Babu
  • Srinivas Yarramalle
  • Suresh Varma Penumatsa
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 166)


In this paper, we present an efficient speaker identification system based on generalized gamma distribution. This system comprises of three basic operations, namely speech features classification and metrics for evaluation. The features extracted using MFCC are passed to shifted delta cepstral coefficients (SDC) and then applied to linear predictive coefficients (LPC) to have effective recognition. To demonstrate our method, a database is generated with 200 speakers for training and around 50 speech samples for testing. Above 90% accuracy reported.


Speaker identification MFCC LPC Generalized Gamma Shifted Delta coefficients 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kos, M., Vlaj, D., Kacic, Z.: Speaker’s gender classification and segmentation using spectral and cepstral feature averaging. In: 18th International Conference on Systems, Signals and Image Processing, IWSSIP 2011 (2011)Google Scholar
  2. 2.
    Razik, J., Sénac, C., Fohr, D., Mella, O., Parlangeau-Valles, N.: Comparision of two speech/Music segmentation systems for audio indexing on Web. In: Proc. of WMSCI 2003, Florida, USA (July 2003)Google Scholar
  3. 3.
    Corneliu Octavian, D., Gavat, I.: Feature Extraction Modeling &Training Strategies in continuous speech Recognition For Roman Language. In: EU Proceedings of IEEE Xplore, EUROCN 2005, pp. 1424–1428 (2005)Google Scholar
  4. 4.
    Agarwal, S., et al.: Prosodic Feature Based Text-Dependent Speaker Recognition Using machine Learning Algorithm. International Journal of Engg. Sc. &Technology 2(10), 5150–5157 (2010)Google Scholar
  5. 5.
    Gonzalez, D.R., Calvo de Lara, J.R.: Speaker verification with shifted delta cepstral features: Its Pseudo-Prosodic Behaviour. In: Proc. I Iberian SLTech. (2009)Google Scholar
  6. 6.
    Torres-Carrasquillo, P.A., Singer, E., Kohlerand, M.A., Greene, R.J., Reynolds, A., Deller Jr., J.R.: Approches to language Identification Using Gausian Mixture Models and Shifted delta cepstral features. In: Proc. of ICSLP 2002, pp. 89–92 (2002)Google Scholar
  7. 7.
    Kinnunen, T., Koh, C.W.E., Wang, L., Li, H., Chang, E.S.: Temporal discrete cosine trans-form: Towards longer term temporal features for speaker verification. In: Proc of ICSLP 2006 (2006)Google Scholar
  8. 8.
    Calvo, J.R., Fernández, R., Hernández, G.: Channel / Handset Mismatch Evaluation in a Biometric Speaker Verification Using Shifted Delta Cepstral Features. In: Rueda, L., Mery, D., Kittler, J. (eds.) CIARP 2007. LNCS, vol. 4756, pp. 96–105. Springer, Heidelberg (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  • K. Suri Babu
    • 1
  • Srinivas Yarramalle
    • 2
  • Suresh Varma Penumatsa
    • 3
  1. 1.NSTL (DRDO), Govt. of IndiaVisakhapatnamIndia
  2. 2.Dept. of ITGITAM UniversityVisakhapatnamIndia
  3. 3.Aadikavi Nannaya UniversityRajahmundryIndia

Personalised recommendations