최소 통계법과 Short-Term 예측계수 코드북을 이용한 Non-Stationary/Mixed 배경잡음 추정 기법 (Non-Stationary/Mixed Noise Estimation Algorithm Based on Minimum Statistics and Codebook Driven Short-Term Predictor Parameter Estimation)

서지정보

· 발행기관 : 한국음향학회
· 수록지 정보 : 한국음향학회지 / 29권 / 3호 / 200 ~ 208페이지
· 저자명 : 이명석, 노명훈, 박성주, 이석필, 김무영

초록

본 논문에서는 배경잡음에 강인한 잡음제거 알고리즘 설계를 위해서 minimum statistics (MS) 기법을 codebook driven short-termpredictor parameter estimation (CDSTP) 기법에접목하는방법을제안한다. MS는stationary 배경잡음에는강인하지만, non-stationary 배경잡음에는 상대적으로 취약하다. CDSTP는 non-stationary 배경잡음에 강인한 특성을보이지만, 코드북에없는배경잡음환경에는취약하다. 따라서non-stationary 배경잡음에강인한CDSTP방법과별도의코드북학습과정이필요없는MS를결합해서다양한배경잡음에강인한알고리즘을제안한다. 제안방법은MS나CDSTP 방법에비해서전체적으로향상된perceptual evaluation of speech quality (PESQ) 성능을나타냈으며, 특히stationary 배경잡음과 non-stationary 배경잡음이 섞여 있는 mixed 배경잡음 환경에서 강인한 특성을 보였다.

영어초록

In this work, the minimum statistics (MS) algorithm is combined with the codebook driven short-term predictor parameter estimation (CDSTP) to design a speech enhancement algorithm that is robust against various background noise environments. The MS algorithm functions well for the stationary noise but relatively not for the non-stationary noise. The CDSTP works efficiently for the non-stationary noise, but not for the noise that was not considered in the training stage. Thus, we propose to combine CDSTP and MS. Compared with the single use of MS and CDSTP,the proposed method produces better perceptual evaluation of speech quality (PESQ) score, and especially works excellent for the mixed background noise between stationary and non-stationary noises.

참고자료

· 없음