The Journal of the Acoustical Society of Korea

The Acoustical Society of Korea (한국음향학회)
권호 표지

Spectral Feature Transformation for Compensation of Microphone Mismatches

  • Jeong, So-Young (Extell Technology Corporation) ;
  • Oh, Sang-Hoon (Department of Information Communication Engineering, Mokwon University) ;
  • Lee, Soo-Young (BSRC and also Department of BioSystems, Korea Advanced Institute of Science and Technology)
  • Published : 2003.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

The distortion effects of microphones have been analyzed and compensated at mel-frequency feature domain. Unlike popular bias removal algorithms a linear transformation of mel-frequency spectrum is incorporated. Although a diagonal matrix transformation is sufficient for medium-quality microphones, a full-matrix transform is required for low-quality microphones with severe nonlinearity. Proposed compensation algorithms are tested with HTIMIT database, which resulted in about 5 percents improvements in recognition rate over conventional CMS algorithm.

Keywords

References

  1. L. Rssore, G. Micca and C. Vair, 'Methods tor microphone equalization in speech recognition,' Proc. Eurospeech, 2415-2418, 1997
  2. X. Huang, A. Acero and H.-W.Hon, Spoken language processing, (Prentice Hall PTR, New Jersey, 2001
  3. T. F. Quatieri, D. A. Reynolds and G. C. O'Leary, 'Estimation of handset nonlinearity with application to speaker recognition,' IEEE Trans. Speech and Audio Processing, 8 (5), 567-584, 2000 https://doi.org/10.1109/89.861376
  4. C. Avendano and H. Hermansky, 'On the effects of short-term spectrum smoothing in channel normalization,' IEEET rans. Speech and Audio Processing, 5 (4), 372-374, 1997 https://doi.org/10.1109/89.593318