Browse > Article

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)
Publication Information
The Journal of the Acoustical Society of Korea / v.22, no.4E, 2003 , pp. 150-154 More about this Journal
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
Microphone mismatches; Feature compensation; Robust speech recognition;
Citations & Related Records
연도 인용수 순위
  • Reference
1 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   DOI   ScienceOn
2 L. Rssore, G. Micca and C. Vair, 'Methods tor microphone equalization in speech recognition,' Proc. Eurospeech, 2415-2418, 1997
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   DOI   ScienceOn
4 X. Huang, A. Acero and H.-W.Hon, Spoken language processing, (Prentice Hall PTR, New Jersey, 2001