Advertisement

Speech Recognition Experiments with Silicon Auditory Models

  • John Lazzaro
  • John Wawrzynek
Part of the The Springer International Series in Engineering and Computer Science book series (SECS, volume 447)

Abstract

Neurophysiologists and psychoacousticans have made fundamental advances in understanding biological audition. Computational models of auditory processing, which allow the quantitative assessment of proposed theories of auditory processing, play an important role in the advancement of auditory science.

Keywords

Feature Vector Speech Recognition Speech Recognition System Auditory Model Auditory Representation 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    N. A. Bhadkamkar. Binaural source localizer chip using subthreshold analog CMOS. In IEEE International Conference on Neural Networks, volume 3, pages 1866–1870, 1994.Google Scholar
  2. [2]
    S. Boll. Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. on ASSP, ASSP-27(2):113–120, 1979.CrossRefGoogle Scholar
  3. [3]
    H. Bourlard and N. Morgan. Connectionist speech recognition: a hybrid approach. Kluwer Academic Publishers, Boston, Mass, 1994.Google Scholar
  4. [4]
    G. J. Brown and M. P. Cooke. Computational auditory scene analysis. Computer Speech and Language, 8(4):297–336, 1994.CrossRefGoogle Scholar
  5. [5]
    A. P. Chandrakasan and R. W. Brodersen. Low power digital CMOS design. Kluwer Academic Publishers, Boston, Mass, 1995.Google Scholar
  6. [6]
    R. Coggins, M. Jabri, B. Flower, and S. Pickard. A hybrid analog and digital VLSI neural network for intracardiac morphology classification. IEEE Journal Solid State Circuits, 30(5):542–550, 1995.CrossRefGoogle Scholar
  7. [7]
    C. Colomes, M. Lever, J. B. Rault, and Y. F. Dehery. A perceptual model applied to audio bit-rate reduction. J. Audio Eng. Soc., 43(4):233–239, 1995.Google Scholar
  8. [8]
    M. Cooke, P. Green, and M. Crawford. Handling missing data in speech recognition. In 1994 International Conference on Spoken Language Processing, volume 3, pages 1555–1558, 1994.Google Scholar
  9. [9]
    O. Ghitza. Temporal non-place information in the auditory nerve firing patterns as a front-end for speech recognition in a noisy environment. Journal of Phonetics, 16(1):109–123, 1988.Google Scholar
  10. [10]
    H. Hermansky. Perceptual linear predictive (plp) analysis of speech. Journal Acoustical Society of America, 87(4):1738–1752, 1990.CrossRefGoogle Scholar
  11. [11]
    H. Hermansky and N. Morgan. Rasta processing of speech. IEEE Transactions of Speech and Audio Processing, 2(4):578–589, 1994.CrossRefGoogle Scholar
  12. [12]
    N. Intrator. Combining exploratory projection pursuit and projection pursuit regression with application to neural networks. Neural Computation, 5:443–455, 1993.Google Scholar
  13. [13]
    C. R. Jackowoski, H. D. H. Vo, and R. P. Lippmann. A comparison of signal processing front ends for automatic word recognition. IEEE Transactions of Speech and Audio Processing, 3(4):286–293, 1995.CrossRefGoogle Scholar
  14. [14]
    J. Lazzaro, J. Wawrzynek, and A. Kramer. Systems technologies for silicon auditory models. IEEE Micro, 14(3):7–15, June 1994.CrossRefGoogle Scholar
  15. [15]
    J. Lazzaro, J. Wawrzynek, M. Mahowald, M. Sivilotti, and D. Gillespie. Silicon auditory processors as computer peripherals. IEEE Journal of Neural Networks, 4(3):523–528, 1993.CrossRefGoogle Scholar
  16. [16]
    J. P. Lazzaro. A silicon model of an auditory neural representation of spectral shape. IEEE Journal Solid State Circuits, 26:772–777, 1991.CrossRefGoogle Scholar
  17. [17]
    J. P. Lazzaro and C. Mead. Circuit models of sensory transduction in the cochlea. In Mead and Ismail, editors, Analog VLSI Implementation of Neural Systems, pages 85–101. Kluwer Academic Publishers, Norwell, MA, 1989.Google Scholar
  18. [18]
    J. P. Lazzaro and C. Mead. Silicon models of auditory localization. Neural Computation, 1:47–57, 1989.CrossRefGoogle Scholar
  19. [19]
    J. P. Lazzaro and C. Mead. Silicon models of pitch perception. In Proc. Natl. Acad. Sci. USA, volume 86, pages 9597–9601, 1989.CrossRefGoogle Scholar
  20. [20]
    J. P. Lazzaro and J. Wawrzynek. A multi-sender asynchronous extension to the address-event protocol. In W. J. Dally, J. W. Poulton, and A. T. Ishii, editors, 16th Conference on Advanced Research in VLSI, pages 158–169, 1995.Google Scholar
  21. [21]
    John Lazzaro. Temporal adaptation in a silicon auditory nerve. In John E. Moody, Steve J. Hanson, and Richard P. Lippmann, editors, Advances in Neural Information Processing Systems, volume 4, pages 813–820. Morgan Kaufmann Publishers, Inc., 1992.Google Scholar
  22. [22]
    John Lazzaro and John Wawrzynek. Silicon models for auditory scene analysis. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems, volume 8, pages 699–705. The MIT Press, 1996.Google Scholar
  23. [23]
    John Lazzaro and John Wawrzynek. Silicon models for auditory scene analysis. In M. Jordan, M. Mozer, and T. Petsche, editors, Advances in Neural Information Processing Systems, volume 9. The MIT Press, 1997.Google Scholar
  24. [24]
    John Lazzaro, John Wawrzynek, and R. Lippmann. A micropower analog VLSI HMM state decoder for wordspotting. In M. Jordan, M. Mozer, and T. Petsche, editors, Advances in Neural Information Processing Systems, volume 9. The MIT Press, 1997.Google Scholar
  25. [25]
    W. Liu, A. Andreou, and M. Goldstein. Voiced-speech representation by an analog silicon model of the auditory periphery. IEEE Transactions of Neural Networks, 3(3):477–487, 1992.CrossRefGoogle Scholar
  26. [26]
    R. F. Lyon. CCD correlators for auditory models. In IEEE Asilomar Conference on Signals, Systems, and Computers, pages 785–789, 1991.Google Scholar
  27. [27]
    R. F. Lyon and C. Mead. An analog electronic cochlea. IEEE Trans. Acoust., Speech, Signal Processing, 36:1119–1134, July 1988.Google Scholar
  28. [28]
    K. W. Ma. Applying large vocabulary hybrid HMM-MLP methods to telephone recognition of digits and natural numbers. Technical Report TR-95-024, International Computer Science Institute, 1995.Google Scholar
  29. [29]
    N. Morgan, H. Bourlard, S. Greenberg, and H. Hermansky. Stochastic perceptual auditory event-based models for speech recognition. In 1994 International Conference on Spoken Language Processing, volume 4, pages 1943–1946, Yokohama, Japan, 1994.Google Scholar
  30. [30]
    M. B. Sachs and E. D. Young. Effects of nonlinearities on speech encoding in the auditory nerve. J. Acoust. Soc. Am, 68(3):858–875, 1980.CrossRefGoogle Scholar
  31. [31]
    S. Seneff. A joint synchrony/mean-rate model of auditory speech processing. Journal of Phonetics, 16(1):55–76, 1988.Google Scholar
  32. [32]
    A. van Schaik, E. Fragnière, and E. A. Vittoz. Improved silicon cochlea using compatible lateral bipolar transistors. In David S. Touretzky, Michael C. Mozer, and Michael E. Hasselmo, editors, Advances in Neural Information Processing Systems, volume 8, pages 671–677. The MIT Press, 1996.Google Scholar
  33. [33]
    E. A. Vittoz. The design of high-performance analog circuits on CMOS chips. EEE Journal Solid State Circuits, 20(3):657–665, 1985.CrossRefGoogle Scholar
  34. [34]
    L. Watts, D. Kerns, R. F. Lyon, and C. Mead. Improved implementation of the silicon cochlea. IEEE Journal Solid-State Circuits, 27(5):692–700, May 1992.CrossRefGoogle Scholar

Copyright information

© Kluwer Academic Publishers 1998

Authors and Affiliations

  • John Lazzaro
    • 1
  • John Wawrzynek
    • 1
  1. 1.CS DivisionUniversity of California at BerkeleyBerkeley

Personalised recommendations