Advertisement

Soft Processing of Audio Signals

  • Andrzej Czyżewski
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 19)

Abstract

The aim of the presented research is to develop and to test some digital signal processing systems applicable to modern telecommunications. A special feature of the elaborated systems is the improvement in performance of audio signal processing algorithms obtained through the use of some soft computing methods based on rough sets, fuzzy logic and neural networks. The engineered and tested digital signal processing systems enabled some comparative studies of the effectiveness of algorithms based on soft computing. The results of speaker-independent recognition of digits and of noise removal from speech and music signals will be presented. Some general conclusions concerning the application of intelligent decision systems to real-time signal processing will be added.

Keywords

Fuzzy Logic Speech Recognition Soft Computing Audio Signal Critical Band 
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.
    Czyzewski, A., Kaczmarek, A.: Multilayer knowledge base system for speaker-independent recognition of isolated words. In: W. Ziarko (ed.): Rough Sets, Fuzzy Sets and Knowledge Discovery (RSKD’93). Workshops in Computing, Springer-Verlag & British Computer Society, London, Berlin (1994) 387–394CrossRefGoogle Scholar
  2. 2.
    Bon, K. Sy, Horowitz, M.: A statistical causal model for the assessment of dysarthric speech and the utility of computer-based speech recognition. In: IEEE Trans. on Biomed. Eng. 40/12 (1993)Google Scholar
  3. 3.
    Zhao, Z.: A rough set approach to speech recognition. The Master Thesis guided by W. Ziarko, Dept. of Computer Science, Regina University, Regina, Saskatchewan (1992)Google Scholar
  4. 4.
    McAulay, R.J., Quatieri, T.F.: Speech analysis synthesis based on a sinusoidal representation. In: IEEE Trans. Acoust., Speech, Signal Processing 34 (1986)Google Scholar
  5. 5.
    Czyzewski, A.: Some methods for detection and interpolation of impulsive distortions in old audio recordings. In: IEEE ASSP Workshop on Application of Signal Processing to Audio and Acoustics, New York, USA (1995)Google Scholar
  6. 6.
    Czyzewski, A., Królikowski, R.: Simultaneous noise reduction and data compression in old audio recordings. In: 101st Audio Engineering Society Convention 4337, Los Angeles, November (1996)Google Scholar
  7. 7.
    Czyzewski, A., Kaczmarek, A.: Speech recognition based on rough sets and neural networks. In: T.Y. Lin, A.M. Wildberger (eds.): Soft Computing: Rough Sets, Fuzzy Logic, Neural Networks, Uncertainty Management, Knowledge Discovery, Simulation Councils, Inc., San Diego, CA (1995) 97–100Google Scholar
  8. 8.
    Czyzewski, A.: Speaker-independent recognition of digits - experiments with neural networks, fuzzy logic and rough sets. In: Journal of Intelligent Automation and Soft Computing (Autosoft) 2/2 (1996) 133–146Google Scholar
  9. 9.
    Kostek, B.: Rough set and fuzzy set methods applied to acoustic analyses. In: Journal of Intelligent Automation and Soft Computing (Autosoft) 2/2 (1996) 147–160Google Scholar
  10. 10.
    Czyzewski, A.: Mining knowledge in noisy audio data. In: E. Simoudis, J. Han, and U. Fayyad (eds.), Second International Conference on Knowledge Discovery and Data Mining, Proceedings (KDD’96), August 2–4, Portland, Oregon, USA, AAAI Press, Menlo Park (1996) 220–225Google Scholar
  11. 11.
    Czyzewski, A., Krolikowski, R.: New methods of intelligent filtration and coding of audio. In: 102nd Audio Engineering Society Convention 4482, Munich, Germany (1997)Google Scholar
  12. 12.
    Czyzewski, A., Kostek, B.: Rough set-based filtration of sound applicable to hearing prostheses. In: S. Tsumoto, S. Kobayashi, T. Yokomori, H. Tanaka, and A. Nakamura (eds.): Proceedings of the Fourth International Workshop on Rough Sets, Fuzzy Sets, and Machine Discovery (RSFD’96), The University of Tokyo, November 6–8 (1996) 168–175Google Scholar
  13. 13.
    Pena, A.S.: A theoretical approach to a generalized auditory model for audio coding and objective perceptual assessment. In: 96th AES Convention 3802, Amsterdam (1994)Google Scholar
  14. 14.
    Czyzewski, A.: Artificial intelligence-based processing of old audio recordings. In: 97th Audio Engineering Society Convention 3885, San Francisco (1994)Google Scholar
  15. 15.
    Nguyen, H.S., Nguyen, S.H.: Discretization of real value attributes for control problems. In: Proceedings of the Fourth European Congress on Intelligent Techniques and Soft Computing (EUFIT’96), September 2–5, Aachen, Germany, Verlag Mainz, Aachen (1996) 188–191Google Scholar
  16. 16.
    McAulay, R.J., Quatieri, T.F.: Speech analysis synthesis based on a sinusoidal representation. In: IEEE Trans. Acoust., Speech, Signal Processing 34 (1986)Google Scholar
  17. 17.
    Czyzewski, A.: New learning algorithms for the processing of old audio recordings. In: 99th Audio Engineering Society Convention 4078, New York (1995)Google Scholar
  18. 18.
    Czyzewski, A., Krolikowski, R., Application of intelligent decision systems to the perceptual noise reduction of audio signals. In: Proceedings of the Fifth European Congress on Intelligent Techniques and Soft Computing (EUFIT’97), September 8–11, Aachen, Germany, Verlag Mainz, Aachen (1997) 188–192Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Andrzej Czyżewski
    • 1
  1. 1.Faculty of Electronics, Telecommunications and Informatics, Sound Engineering DepartmentTechnical University of GdanskGdanskPoland

Personalised recommendations