Incorporation of IMM-based Feature Compensation and Uncertainty Decoding 


Vol. 37,  No. 6, pp. 492-496, Jun.  2012


PDF
  Abstract

This paper presents a decoding technique for speech recognition using uncertainty information from feature compensation method to improve the speech recognition performance in the low SNR condition. Traditional feature compensation algorithms have difficulty in estimating clean feature parameters in adverse environment. Those algorithms focus on the point estimation of desired features. The point estimation of feature compensation method degrades speech recognition performance when incorrectly estimated features enter into the decoder of speech recognition. In this paper, we apply the uncertainty information from well-known feature compensation method, such as IMM, to the recognition engine. Applied technique shows better performance in the Aurora-2 DB.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

S. J. Kang, C. W. Han, K. Kwon, N. S. Kim, "Incorporation of IMM-based Feature Compensation and Uncertainty Decoding," The Journal of Korean Institute of Communications and Information Sciences, vol. 37, no. 6, pp. 492-496, 2012. DOI: .

[ACM Style]

Shin Jae Kang, Chang Woo Han, Kisoo Kwon, and Nam Soo Kim. 2012. Incorporation of IMM-based Feature Compensation and Uncertainty Decoding. The Journal of Korean Institute of Communications and Information Sciences, 37, 6, (2012), 492-496. DOI: .

[KICS Style]

Shin Jae Kang, Chang Woo Han, Kisoo Kwon, Nam Soo Kim, "Incorporation of IMM-based Feature Compensation and Uncertainty Decoding," The Journal of Korean Institute of Communications and Information Sciences, vol. 37, no. 6, pp. 492-496, 6. 2012.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880