SPEAKER VERIFICATION SYSTEM - Based on the stochastic modeling

Valiantsin Rakush, Rauf Kh. Sadykhov

2004

Abstract

In this paper we propose a new speaker verification system where the new training and classification algorithms for vector quantization and Gaussian mixture models are introduced. The vector quantizer is used to model sub-word speech components. The code books are created for both training and test utterances. We propose new approaches to normalize distortion of the training and test code books. The test code book quantized over the training code book. The normalization technique includes assigning the equal distortion for training and test code books, distortion normalization and cluster weights. Also the LBG and K-means algorithms usually employed for vector quantization are implemented to train Gaussian mixture models. And finally, we use the information provided by two different models to increase verification performance. The performance of the proposed system has been tested on the Speaker Recognition database, which consists of telephone speech from 8 participants. The additional experiments has been performed on the subset of the NIST 1996 Speaker Recognition database which include.

References

  1. Roberts, W.J.J., Wilmore J.P., 1999. Automatic speaker recognition using Gaussian mixture models. In Proceedings of Information, Decision and Control, IDC 99.
  2. Farrell, K., Kosonocky, S., Mammone, R., 1994. Neural tree network/vector quantization probability estimators for speaker recognition. In Proceedings of the Neural Networks for Signal Processing, IEEE Workshop.
  3. Burton, D., 1987. Text-dependent speaker verification using vector quantization source coding. In Acoustics, Speech, and Signal Processing, IEEE Transactions.
  4. Zilca, R.D., 2001. Text-independent speaker verification using covariance modeling. In Signal Proceesing Letters, IEEE.
  5. Moonsar, V., Venayagamorthy, G.K., 2001. A committee of neural networks for automatic speaker recognition (ASR) systems. In Proceedings of International Joint Conference on Neural Networks, IJCNN'01.
  6. Pelecanos, J., Myers, S., Shridharan, S., Chandran, V., 2000. Vector quantization based Gaussian modeling for speaker verification, In Proceedings of 15th International Conference on Pattern Recognition.
  7. Chun-Nan Hsu, Hau-Chang Yu, Bo-Han Yang, 2003. Speaker verification without background speaker models, In Acoustics, Speech, and Signal Processing, IEEE International Conference, ICASSP'03.
  8. Homayounpour, M.M., Challet, G., 1995. Neural net approach to speaker verification: comparison with second order statistics measures, In Acoustics, Speech, and Signal Processing, IEEE International conference, ICASSP-95.
  9. Singh, G., Panda, A., Bhattacharyga, S., Srikanthan, T., 2003. Vector quantization techniques for GMM based speaker verification, In Acoustics, Speech, and Signal Processing, IEEE International Conference, ICASSP'03.
  10. Farrell, K. R., Ramachandran, R.P., Mammone, R.J., 1998. An analysis of data fusion methods for speaker verification, In Acoustics, Speech, and Signal Processing, IEEE International Conference, ICASSP'98.
  11. Farrell, K.R., Ramachandran, R.P., Sharman, M., Mammone, R.J., 1997. Sub-word speaker verification using data fusion methods. In Neural Networks for Signal Processing, Proceedings of the IEEE Workshop.
  12. Sadykhov, R. Kh., Rakush, V.V., 2003, Training Gaussian models with vector quantization for speaker verification, In Proceedings of the 3rd International Conference on Neural Networks and Artificial Intelligence.
  13. Rakush V.V., Sadykhov R.H., 1999, Speaker Identification System on Arbitrary Speech In Pattern Recognition and Information Processing. Proc. Of 5th International Conference.
  14. The NIST year 2002 speaker recognition evaluation plan, 2002, http://www.nist.gov/speech/tests/spk/2002/doc.
Download


Paper Citation


in Harvard Style

Rakush V. and Sadykhov R. (2004). SPEAKER VERIFICATION SYSTEM - Based on the stochastic modeling . In Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO, ISBN 972-8865-12-0, pages 183-189. DOI: 10.5220/0001132901830189


in Bibtex Style

@conference{icinco04,
author={Valiantsin Rakush and Rauf Kh. Sadykhov},
title={SPEAKER VERIFICATION SYSTEM - Based on the stochastic modeling},
booktitle={Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,},
year={2004},
pages={183-189},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001132901830189},
isbn={972-8865-12-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 3: ICINCO,
TI - SPEAKER VERIFICATION SYSTEM - Based on the stochastic modeling
SN - 972-8865-12-0
AU - Rakush V.
AU - Sadykhov R.
PY - 2004
SP - 183
EP - 189
DO - 10.5220/0001132901830189