Abstract
Here wavelet based features in combination with Spectral-Subtraction (SS) are proposed for speaker identification in clean and noisy environment. Gaussian Mixture Models (GMMs) are used as a classifier for classification of speakers. The identification performance of Linear Prediction Coefficient (LPC), Wavelet LPC (WLPC), and Spectral Subtraction WLPC (SS-WLPC) features are computed and compared. WLPC features have shown higher performance over the conventional methods in clean and noisy environment. SS-WLPC features have shown further improvements over WLPC features for speaker identification. Database of fifty speakers for ten Hindi digits are used.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Rabiner, L.R., Juang, B.H.: Fundamentals of Speech Recognition, 1st edn. Pearson Education, Delhi (2003)
Reynolds, D.A., Rose, R.C.: Robust Text-Independent Speaker Identification using Gaussian Mixture Speaker Models. IEEE Transactions on Speech and Audio Processing 3(1), 74–77 (1995)
Makhoul, J.: Linear prediction: A tutorial review. Proc. of IEEE 63(4), 561–580 (1975)
Ranjan.: A Discrete Wavelet Transform Based Approach to Hindi Speech Recognition. In: Proceedings of the International Conference on Signal Acquisition and Processing (ICSAP), pp. 345–348 (August 2010)
Wang, K., Lee, C.H., Juang, B.H.: Selective feature extraction via signal decomposition. IEEE Signal Processing Letters 4, 8–11 (1997)
Tufekci, Z., Gowdy, J.N.: Feature extraction using discrete wavelet transform for speech recognition. In: IEEE International Conference Southeastcon 2000, Nashville, TN, USA, pp. 116–123 (April 2000)
Farooq, O., Datta, S.: Mel filter-like admissible wavelet packet structure for speech recognition. IEEE Signal Process. Lett. 8(7), 196–198 (2001)
Sharma, A., Shrotriya, M.C., Farooq, O., Abbasi, Z.A.: Hybrid Wavelet based LPC Features for Hindi Speech Recognition. International Journal of Information and Communication Technology 1(3/4), 373–381 (2008)
Sharma, R.P., Farooq, O., Khan, I.: Wavelet based sub-band parameters for classification of unaspirated Hindi stop consonants in initial position of CV syllables. Int. J. Speech Technol. 16(3), 323–332 (2012)
Berouti, A., et al.: Enhancement of speech corrupted by acoustic noise. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 1979), pp. 208–211 (1979)
Aida–Zade, K.R., Ardil, C., Rustamo, S.S.: Investigation of Combined use of MFCC and LPC Features in Speech Recognition Systems. World Academy of Science, Engineering and Technology 2006, 74–77 (2006)
Gupta, V.K., Bhowmick, A., Chandra, M., Sharan, S.N.: Speech Enhancement Using MMSE Estimation and Spectral Subtraction Methods. In: 2011 International Conference on Devices and Communications (ICDeCom), February 24-25, pp. 1–5 (2011)
Chowdhury, M.F.R.: Text independent distributed speaker identification and verification using GMM UBM speaker models for mobile communications. In: 10th International Conference on Information Science, Signal Processing and Their Application, pp. 57–60 (2010)
Gong, Y.: Noise-robust open-set speaker recognition using noise-dependent Gaussian mixture classifier. In: Proc. ICASSP, pp. 133–136 (2002)
Srivastava, S., Nandi, P., Sahoo, G., Chandra, M.: Formant Based Linear Prediction Coefficients for Speaker Identification. In: 2014 International Conference on Signal Processing and Integrated Networks (SPIN), Noida, Delhi-NCR, India, February 20-21, pp. 685–688 (2014)
Varga, A., Steeneken, H.J.M., Jones, D.: The noisex-92 study on the effect of additive noise on automatic speech recognition system. Reports of NATO Research Study Group (RSG.10) (June 1992)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Chandra, M., Nandi, P., kumari, A., Mishra, S. (2015). Spectral-Subtraction Based Features for Speaker Identification. In: Satapathy, S., Biswal, B., Udgata, S., Mandal, J. (eds) Proceedings of the 3rd International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA) 2014. Advances in Intelligent Systems and Computing, vol 328. Springer, Cham. https://doi.org/10.1007/978-3-319-12012-6_58
Download citation
DOI: https://doi.org/10.1007/978-3-319-12012-6_58
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12011-9
Online ISBN: 978-3-319-12012-6
eBook Packages: EngineeringEngineering (R0)