International Journal of Fuzzy Logic and Intelligent Systems

  • 제5권1호
  • /
  • Pages.76-82
  • /
  • 2005
  • /
  • 1598-2645(pISSN)
  • /
  • 2093-744X(eISSN)
한국지능시스템학회 (Korean Institute of Intelligent Systems)
권호 표지
DOI QR코드

DOI QR Code

Speaker Identification Based on Incremental Learning Neural Network

  • Heo, Kwang-Seung (School of Electrical and Electronic Engineering, Chung-Ang University) ;
  • Sim, Kwee-Bo (School of Electrical and Electronic Engineering, Chung-Ang University)
  • 발행 : 2005.03.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Speech signal has various features of speakers. This feature is extracted from speech signal processing. The speaker is identified by the speaker identification system. In this paper, we propose the speaker identification system that uses the incremental learning based on neural network. Recorded speech signal through the microphone is blocked to the frame of 1024 speech samples. Energy is divided speech signal to voiced signal and unvoiced signal. The extracted 12 orders LPC cpestrum coefficients are used with input data for neural network. The speakers are identified with the speaker identification system using the neural network. The neural network has the structure of MLP which consists of 12 input nodes, 8 hidden nodes, and 4 output nodes. The number of output node means the identified speakers. The first output node is excited to the first speaker. Incremental learning begins when the new speaker is identified. Incremental learning is the learning algorithm that already learned weights are remembered and only the new weights that are created as adding new speaker are trained. It is learning algorithm that overcomes the fault of neural network. The neural network repeats the learning when the new speaker is entered to it. The architecture of neural network is extended with the number of speakers. Therefore, this system can learn without the restricted number of speakers.

키워드

참고문헌

  1. N. Mohankrishnan, M. Shridhar, M.A. Sid-Ahmed 'A Composite Scheme for Text-Independent Speaker Recognition,' Acoustic, Speech and Signal Processing, IEEE International Conference on'82, vol. 7, pp. 1653-1656, 1982 https://doi.org/10.1109/ICASSP.1982.1171437
  2. S. Pruzansky, 'Pattern-matching procedure for automatic talker recognition,' J. Acoustic. Soc. Amer, vol. 35, pp. 354-358, Apr 1971
  3. F.K. Soong, A.E. Rosenberg, L.R. Rabiner, B.H. Juang, 'A vector quantization approach to speaker recognition,' in Proc. ICASSP, pp. 387-390, 1985
  4. Kevin R.Farrell, Richard J.Mammone, Khaled T.Assaleh, 'Speaker Recognition Using Neural Networks and Conventional Classifiers,' IEEE Transaction on speech and audio processing, vol. 2, no. 1, pp. 194-205, January 1994 https://doi.org/10.1109/89.260362
  5. K.Farrell, R.J.Mammone, A.L.Gorin, 'Adaptive Language Acqusition Using Incremental Learning,' Acoustics, Speech, and Signal Processing, 1993, ICASSP-93, 1993, IEEE International conference on, vol. 1, pp. 501-504, Apr 1993 https://doi.org/10.1109/ICASSP.1993.319165
  6. R.Poliker, L.Udpa, S.S.Udpa, V.Honavar, 'Learn++: An Incremental Learning algorithm for Multilayer perceptron networks,' Acoustic, Speech and Signal Processing, 2000, ICASSP'00, Proceedings, 2000, IEEE International Conference on, vol. 6, pp. 3414-3417, 2000
  7. Jin-soo Han, Speech Signal Processing, Osung Media, 2000
  8. A.M. Kondoz, Digital Speech coding for low bit rate communications systems, John Wiley & Sons, 1994
  9. Lawrence Rabiner, Biing-Hwang Juang, Fundamentals of speech recognition, Prentice-Hall International Inc., 1993
  10. Xuedong Huang, Alex Acero, Hsiao-Wuen Hon, Spoken Language Processing A guide to Theory, Algorithm, and System Development
  11. Raul Rojas, Neural Networks A systematic Introduction, Springer, 1996
  12. Simon Haykin, Adaptive Filter theory, Prentice Hall Information And System Science Series, 2001
  13. Koichiro Yamauchi, Nobuhiko Yamaguchi, Naohiro Ishii, 'Incremental Learning Methods with Retrieving of ..Interfered Patterns,' IEEE Transaction on Neural Network, vol. 10, no. 6, pp. 1351-1365, November 1999 https://doi.org/10.1109/72.809080
  14. D. C. Park, M. A. E1-Sharkawi, R. J. Marks II, 'An adaptively trained neural network,' IEEE Trans. Neural Network, vol. 2, pp. 334-345, May 1991 https://doi.org/10.1109/72.97910
  15. T. Yoneda, M. Yamanaka, Y. Kakazu, 'Study on optimization of grinding conditions using neural networksA method of additional learning,' J. Japan Soc. Precision Eng., vol. 58, no. 10, pp. 1707-1712, Oct 1992 https://doi.org/10.2493/jjspe.58.1707