Voice Identification Using Nonparametric Density Matching

  • A. Higgins
  • L. Bahler
  • J. Porter
Part of the The Kluwer International Series in Engineering and Computer Science book series (SECS, volume 355)


Text-independent speaker recognition is often based on the premise that acoustic measurements derived from the speech utterances of an individual are characterized by stable, speaker-unique probability density functions (PDFs). This chapter describes a method of comparing speech utterances to determine whether or not the underlying PDFs are the same, hence likely to have been spoken by the same person. The method is independent of assumptions about the form of the PDFs. Based on a conjecture regarding the local relationship between probability density and nearest-neighbor distance, the algorithm is shown to measure global differences between the speakers’ underlying feature distributions. Experimental results are presented for the King telephone database.


Test Point Speaker Recognition Speaker Identification Input Speech Affine Connection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    T. Matsui and S. Furui, “Concatenated phoneme models for text-variable speaker recognition,” Proc. ICASSP-93, volume II, pp. 391–394, Minneapolis, April 1993.Google Scholar
  2. [2]
    Y. H. Kao, P. K. Rajasekaran, and J. S. Baras, “Robust free-text speaker identification over long distance telephone channels,” Proc. ICASSP-93, Minneapolis, April 1993.Google Scholar
  3. [3]
    A. E. Rosenberg, C. H. Lee, and F. K. Soong, “Sub-word unit talker verification using hidden Markov models,” Proc. ICASSP-90, pp. 269–272, Albuquerque, New Mexico, April 1990.Google Scholar
  4. [4]
    L. Gillick, J. Baker, J. Baker, J. Bridle, M. Hunt, Y. Ito, S. Lowe, J. Orloff, B. Peskin, R. Roth, and F. Scattone, “Application of large vocabulary continuous speech recognition to topic and speaker identification using telephone speech,” Proc. ICASSP-93, volume II, pp. 471–474, Minneapolis, April 1993.Google Scholar
  5. [5]
    C. Olano, “An investigation of spectral match statistics using a phonetically marked data base,” Proc. ICASSP-83, 1983.Google Scholar
  6. [6]
    J. D. Markel, B. T. Oshika, and A. H. Gray Jr., “Long-term feature averaging for speaker recognition,” IEEE Trans, on Acoustics, Speech, and Signal Processing, volume ASSP-25, pp. 330–337, 1977.CrossRefGoogle Scholar
  7. [7]
    H. Gish, K. Karnofsky, M, Krasner, S. Roucos, R. Schwartz, and J. Wolf, “Investigation of text-independent speaker identification over telephone channels,” Proc. ICASSP-85, volume 1, pp. 379–382, Tampa, FL, 1985.Google Scholar
  8. [8]
    H. Gish, “Robust discrimination in automatic speaker identification,” Proc. ICASSP-90, pp. 289–292, 1990.Google Scholar
  9. [9]
    R. Rose and D. Reynolds, “Text independent speaker identification using automatic acoustic segmentation,” Proc. ICASSP-90, pp. 293–296, 1990.Google Scholar
  10. [10]
    F. Soong, A. Rosenberg, L. Rabiner, and B. Juang, “A vector quantization approach to speaker recognition,” Proc. ICASSP-85, volume 1, pp. 387–390, Tampa, FL, 1985.Google Scholar

Copyright information

© Kluwer Academic Publishers 1996

Authors and Affiliations

  • A. Higgins
    • 1
  • L. Bahler
    • 1
  • J. Porter
    • 1
  1. 1.ITT Aerospace/Communications DivisionSan DiegoUSA

Personalised recommendations