Speech Noise Cancellation using Time Adaptive Threshold Value in Wavelet Transform

  • Lee Chul-Hee (Dept. of Electronic Engineering, Chonbuk National University) ;
  • Lee Ki-Hoon (Dept. of Electronic Engineering, Chonbuk National University) ;
  • Hwang Hyang-Ja (Radioactive Materials Regulation Dept. 2 of Radiation Safety Center, Korea Institute of Nuclear Safety) ;
  • Moon In-Seob (Dept. of Information & Communication Engineering, Chosun College of Science & Technology) ;
  • Kim Chong-Kyo (Dept. of Electronic Engineering, Chonbuk National University)
  • 발행 : 2004.08.01

초록

This paper proposes a new noise cancellation method for speech recognition in noise environments. We determine the time adaptive threshold value using standard deviations of wavelet coefficients after wavelet transform by frames. The time adaptive threshold value is set up by using sum of standard deviations of wavelet coefficients in cA3 and weighted cD1. cA3 coefficients represent the voiced sound with lower frequency components and cD1 coefficients represent the unvoiced sound with higher frequency components. In experiments, we removed noise after adding white Gaussian noise and colored noise to original speech. The proposed method improved SNR and MSE more than wavelet transform and wavelet packet transform does. As a result of speech recognition experiment using noise speech DB, recognition performance is improved by $2\sim4\;\%.$

키워드