Feature extraction for robust speech recognition based on maximizing the sharpness of the power distribution and on power flooring

@article{Kim2010FeatureEF,
  title={Feature extraction for robust speech recognition based on maximizing the sharpness of the power distribution and on power flooring},
  author={Chanwoo Kim and Richard M. Stern},
  journal={2010 IEEE International Conference on Acoustics, Speech and Signal Processing},
  year={2010},
  pages={4574-4577}
}
This paper presents a new robust feature extraction algorithm based on a modified approach to power bias subtraction combined with applying a threshold to the power spectral density. Power bias level is selected as a level above which the signal power distribution is sharpest. The sharpness is measured using the ratio of arithmetic mean to the geometric mean of medium-duration power. When subtracting this bias level, power flooring is applied to enhance robustness. These new ideas are employed… CONTINUE READING
Highly Influential
This paper has highly influenced 25 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 119 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 82 extracted citations

119 Citations

0102030'11'13'15'17
Citations per Year
Semantic Scholar estimates that this publication has 119 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 12 references

Missing-Feature Methods for Robust Automatic Speech Recognition

  • B. Raj, R. M. Stern
  • IEEE Signal Processing Magazine, vol. 22, no. 5…
  • 2005
1 Excerpt

Similar Papers

Loading similar papers…