Current Trends in Signal Processing

Principal Component Analysis Based Dominant Features Selection Method for Speaker Identification

  1. Md. Ekramul Hamid ✉
  2. Md. Khademul Islam Molla
  3. Wade Ghribi

Abstract

Cepstrum based features are mostly used in speaker identification. Mel-frequency cepstrum coefficients (MFCCs) and their statistical properties (skewness, kurtosis and standard deviation) are used in this paper for text-dependent speaker identification. Principal component analysis (PCA) is employed to select the dominant feature vector representing the speaker characteristics. Multi-layer neural network is used as the classification engine. There occurs the inter-speaker variation of speech length uttering the same word. The feature speaker specific vector of defined dimension is derived with PCA. The statistical properties of the selected features and the effects of the first MFCC are studied in terms of speaker identification performance and convergence speed of neural network as illustrated by the experimental results.

References (14)

  1. Mammone R. J. , Zhang X. & Ramachandran R. IEEE Signal processing Magazine September 1996.
  2. Raynolds D. A. IEEE Transacti on on Speech and Audio Processing Oct 1994. 2(4).
  3. Quatiery T. F. Discrete-Time Speech Signal Processing - Principles and Practice Prentice Hall Signal Processing Series. 2001.
  4. Shao Y. & Wang D. ICASSP 2003.
  5. Sae-Tang S. & Tanprasert C. International Symposium on Circuits and Systems (ISCAS) 2000.
  6. Premakanthan P. & Michael W. B. ISCAS 2001.
  7. Cordella L. P., Foggia P., Sansone C. et al. IEEE International Conference on Image Analysis and Proceeding 2003.
  8. Yu K., Mason J. & Oglesby J. IEE Current Trends in Signal Processing Volume 1, Issue 1-3 Compilation 2011 ISSN: 2249-4707© STM Journals 2011. All Rights Reserved. Page 45 Proceedings-Visual Ima ge Signal Processing Oct 1995. 142(5).
  9. Sakuriya S. et al. Twentieth IASTED International Conference on Modeling , Identification and Control (MIC2001) 2001.
  10. Toutios A. & Margaritis K. G. 2nd Hellenic Conference on AI, Thessaloniki, Greece; Proceedings Companion Volume, April 2002. 525–530p.
  11. Molla M. K. I. & Hirose K. IEEE VECIMS Boston, MA, USA. April 2004. 136–141p.
  12. Holmes J. & Holmes W. Speech Synthesis and Recognition Taylor & Francis. 2001.
  13. Casey M. A. Auditory Group Theory: wi th application to statistical basis methods for structured audio PhD thesis, MIT Media Laboratory. 1998.
  14. Uhle C., Dittmar C. & Sporer T. International Symposium on Independent Component Analysis (ICA) Nara, Japan . April 2003.

Read more of it

Subscribe to one journal or build your own list of several. One invoice, one payment, access for a full year.

Subscribe to journals →

Publish your article

Peer-reviewed journals across every subject, with open access options. Send your manuscript to the right editor today.

Publish with us → Calculate your APC
Support