Channel Robust MFCCs for Continuous Speech Speaker Recognition

  • Sharada Vikram Chougule
  • Mahesh S. Chavan
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 264)


Over the years, MFCC (Mel Frequency Cepstral Coefficients), has been used as a standard acoustic feature set for speech and speaker recognition. The models derived from these features gives optimum performance in terms of recognition of speakers for the same training and testing conditions. But mismatch between training and testing conditions and type of channel used for creating speaker model, drastically drops the performance of speaker recognition system. In this experimental research, the performance of MFCCs for closed-set text independent speaker recognition is studied under different training and testing conditions. Magnitude spectral subtraction is used to estimate magnitude spectrum of clean speech from additive noise magnitude. The mel-warped cepstral coefficients are then normalized by taking their mean, referred as cepstral mean normalization used to reduce the effect of convolution noise created due to change in channel between training and testing. The performance of this modified MFCCs, have been tested using Multi-speaker continuous (Hindi) speech database (By Department of Information Technology, Government of India). Use of improved MFCC as compared to conventional MFCC perk up the speaker recognition performance drastically.


Text independent speaker recognition MFCC magnitude spectral subtraction cepstral mean normalization 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Shao, Y., Wang, D.: Robust speaker identification using auditory features and computational auditory scene analysis. In: ICASSP. IEEE (2008)Google Scholar
  2. 2.
    Mammone, R.J., Zhang, X., Ramachandran, R.P.: Robust Speaker Recognition: A Feature based approach. In: IEEE Signal Processing Magazine (September 1996)Google Scholar
  3. 3.
    Rabiner, L., Schafer, R.: Digital Processing of Speech Signal. Prentice Hall, Inc., Englewood Cliffs (1978)Google Scholar
  4. 4.
    Hermansky, H.: Perceptual linear predictive (PLP) analysis for speech. J. Acoust. Soc. Am., 1738–1752 (1990)Google Scholar
  5. 5.
    Wang, N., Ching, P.C.: Robust Speaker Recognition Using Denoised Vocal Source and Vocal Tract Features. IEEE Transactions on Audio, Speech, and Language Processing 19(1) (January 2011)Google Scholar
  6. 6.
    Kinnunen, T., Li, H.: An Overview of Text-Independent Speaker Recognition: From Features to Supervectors. In: Speech Communication (2010)Google Scholar
  7. 7.
    Nosratighods, M., Ambikairajah, E., Epps, J.: Speaker Verification Using A Novel Set of Dynamic Features. In: Pattern Recognition, ICPR 2006 (2006)Google Scholar
  8. 8.
    Openshaw, J., Sun, Z., Mason, J.: A comparison of composite features under degraded speech in speaker recognition. In: IEEE Proceedings of the International Conference on Acoustics, Speech and Signal Processing, vol. 2, pp. 371–374 (1993)Google Scholar
  9. 9.
    Reynolds, D., Rose, R.: Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Trans. on Speech and Audio Processing 3 (January 1995)Google Scholar
  10. 10.
    Campbell Jr., J.P.: Speaker Recognition- A Tutorial. Proceedings of The IEEE 85(9), 1437–1462 (1997)CrossRefGoogle Scholar
  11. 11.
    Lawson, A., Vabishchevich, P., Huggins, M., Ardis, P., Battles, B., Stauffer, A.: Survey and Evaluation of Acoustic Features for Speaker Recognition. In: ICASSP 2011. IEEE (2011)Google Scholar
  12. 12.
    Reynolds, D.A.: An Overview of Automatic Speaker Recognition Technology. In: ICASSP 2001. IEEE (2001)Google Scholar
  13. 13.
    Glsh, H., Schmidt, M.: Text Independent Speaker Identification. In: IEEE Signal Processing Magazine (1994)Google Scholar
  14. 14.
    Prasad, V., Sangwan, R., et al.: Comparison of voice activity detection algorithms for VoIP. In: Proc. of the Seventh International Symposium on Computers and Communications, Taormina, Italy, pp. 530–532 (2002)Google Scholar
  15. 15.
    Menéndez-Pidal, X., Chan, R., Wu, D., Tanaka, M.: Compensation of channel and noise distortions combining normalization and speech enhancement techniques. Speech Communication 34, 115–126 (2001)CrossRefMATHGoogle Scholar
  16. 16.
    Linde, Y., Buzo, A., Gray, R.M.: An algorithm for vector quantizer design. IEEE Trans. Commun. 28(1), 84–95 (1980)CrossRefGoogle Scholar
  17. 17.
    Samudravijaya, K., Ra0, P.V.S., Agrawal, S.S.: Hindi Speech Database. In: Proceedings of International Conference on Spoken Language Processing, China (2000)Google Scholar
  18. 18.
    Vaseghi, S.V.: Advanced Digital Signal Processing and Noise Reduction, 2nd edn. John Wiley & Sons Ltd. (2000)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Sharada Vikram Chougule
    • 1
  • Mahesh S. Chavan
    • 2
  1. 1.Department of Electronics and Telecommunication EngineeringFinolex Academy of Management and TechnologyRatnagiriIndia
  2. 2.Department of Electronics EngineeringKIT’s College of EngineeringKolhapurIndia

Personalised recommendations