Skip to main content

Model Compensation Approach Based on Nonuniform Spectral Compression Features for Noisy Speech Recognition

Abstract

This paper presents a novel model compensation (MC) method for the features of mel-frequency cepstral coefficients (MFCCs) with signal-to-noise-ratio- (SNR-) dependent nonuniform spectral compression (SNSC). Though these new MFCCs derived from a SNSC scheme have been shown to be robust features under matched case, they suffer from serious mismatch when the reference models are trained at different SNRs and in different environments. To solve this drawback, a compressed mismatch function is defined for the static observations with nonuniform spectral compression. The means and variances of the static features with spectral compression are derived according to this mismatch function. Experimental results show that the proposed method is able to provide recognition accuracy better than conventional MC methods when using uncompressed features especially at very low SNR under different noises. Moreover, the new compensation method has a computational complexity slightly above that of conventional MC methods.

References

  1. 1.

    Chu KK, Leung SH: SNR-dependent non-uniform spectral compression for noisy speech recognition. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '04), May 2004, Montreal, Quebec, Canada 1: 973–976.

    Google Scholar 

  2. 2.

    Lotter T, Benien C, Vary P: Multichannel direction-independent speech enhancement using spectral amplitude estimation. EURASIP Journal on Applied Signal Processing 2003,2003(11):1147-1156. 10.1155/S1110865703305025

    MATH  Google Scholar 

  3. 3.

    Gales MJF, Young SJ: Cepstral parameter compensation for HMM recognition in noise. Speech Communication 1993,12(3):231-239. 10.1016/0167-6393(93)90093-Z

    Article  Google Scholar 

  4. 4.

    Gales MJF, Young SJ: Robust continuous speech recognition using parallel model combination. IEEE Transactions on Speech and Audio Processing 1996,4(5):352-359. 10.1109/89.536929

    Article  Google Scholar 

  5. 5.

    Hung J-W, Shen J-L, Lee L-S: New approaches for domain transformation and parameter combination for improved accuracy in parallel model combination (PMC) techniques. IEEE Transactions on Speech and Audio Processing 2001,9(8):842-855. 10.1109/89.966087

    Article  Google Scholar 

  6. 6.

    Moreno PJ, Raj B, Stern RM: A vector Taylor series approach for environment-independent speech recognition. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '96), May 1996, Atlanta, Ga, USA 2: 733–736.

    Google Scholar 

  7. 7.

    Gong Y: Speech recognition in noisy environments: a survey. Speech Communication 1995,16(3):261-291. 10.1016/0167-6393(94)00059-J

    Article  Google Scholar 

  8. 8.

    Zwicker E, Fastl H: Psychoacoustics, Facts and Models. 2nd edition. Springer, New York, NY, USA; 1999.

    Google Scholar 

  9. 9.

    Hermansky H: Perceptual linear predictive (PLP) analysis of speech. Journal of the Acoustical Society of America 1990,87(4):1738-1752. 10.1121/1.399423

    Article  Google Scholar 

  10. 10.

    Abramowitz M, Stegun IA: Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. Dover, New York, NY, USA; 1972.

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Geng-Xin Ning.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Ning, G., Wei, G. & Chu, K. Model Compensation Approach Based on Nonuniform Spectral Compression Features for Noisy Speech Recognition. EURASIP J. Adv. Signal Process. 2007, 032546 (2007). https://doi.org/10.1155/2007/32546

Download citation

Keywords

  • Computational Complexity
  • Quantum Information
  • Static Feature
  • Reference Model
  • Speech Recognition