Earticle

초록

영어

Speech recognition, the problem of performance degradation is the difference between the model training and recognition environments. Silence features normalized using the method as a way to reduce the inconsistency of such an environment. Silence features normalized way of existing in the low signal-to-noise ratio. Increase the energy level of the silence interval for speech and non-speech classification accuracy due to the falling. There is a problem in the recognition performance is degraded. This paper proposed a robust speech detection method in noisy environments using a SFN (silence feature normalization) and SEM (speech energy maximize). In the high signal-to-noise ratio for the proposed method was used to maximize the characteristics receive less characterized the effects of noise by the speech energy. Cepstral feature distribution of speech and non-speech characteristics in the low signal-to-noise ratio and improves the recognition performance. Result of the recognition experiment, recognition performance improved compared to the conventional method.

목차

Abstract
 1. Introduction
 2. Related Work
  2.1. Spectral Energy
  2.2. Critical Band
 3. Voice Detection that Excel in Noise Environment
  3.1. Voice Energy Maximization
  3.2. Silence Feature Normalization
 4. Experiment Result
 5. Conclusion
 References

키워드

저자

• In-Sung Han [ Dept. of The 2nd R&D Institute, Agency for Defense Development 460,Songpa-gu, Seoul, 138-600, South Korea ]
• Chan-Shik Ahn [ Dept. of Computer Engineering, Kwangwoon University 20, Gwangun-ro, Nowon-gu, Seoul, South Korea ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Multimedia and Ubiquitous Engineering

• 간기

  월간

• pISSN

  1975-0080

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605