본문 바로가기
KERD
논문KCI 등재

Active Noise Cancellation using a Teacher Forced BSS earning Algorithm

0

조회

0

다운로드

0

인용

0

참고문헌

주제분류공학일반

초록

Abstract

In this paper, we propose a new Active Noise Control (ANC) system using a teacher forced Blind Source Separation(BSS) algorithm. The Blind Source Separation based on the Independent Component Analysis (ICA) separates the desiredsound signal from the unwanted noise signal. In the proposed system, the BSS algorithm is used as a preprocessor ofANC system. Also, we develop a teacher forced BSS learning algorithm to enhance the performance of BSS. The teachersignal is obtained from the output signal of the ANC system. Computer experimental results show that the proposed ANCsystem in conjunction with the BSS algorithm effectively cancels only the ship engine noise signal from the linear andconvolved mixtures with human voice.

참고문헌 (13)

  1. "Active noise control systems; Algorithm and DSP Implementations", pp.1~51 (1996)
  2. "A multiple error LMS algorithm and its application to the active control of sound and vibration", assp-35(10), pp.1423~1434 (1987)
  3. "The behavior of a multiple channel active control system", 40(5), pp.1041~1052 (1992)
  4. "Adaptive on-line learning algorithms for blind separation: Maximum entropy and minimum mutual information", 9, pp.1457~1482 (1997)
  5. "Blind separation of delayed Sources based on information maximization", pp.7~10 (1996), speech & signal processing
  6. "Blind source separation of real world signals", 4, pp.2129~2134 (1997)
  7. "Active noise control for selective attention using blind source separation", pp.198~203 (1999)
  8. "Selective attention system using active noise controller", 31, pp.197~204 (2000)
  9. "Independent component analysis, theory and applications", pp.27~66 (1998), Kluwer Academic Publishers
  10. "Blind source separation of more sources than mixtures using overcomplete representations", 4, pp.~4 (1999)
  11. "Combining ICA and topdown attention for robust speech recognition", 13 (2000)
  12. "Neural control-ler of nonlinear dynamic systems using higher order neural networks", 28(3), pp.276~277 (1992)
  13. "Learning algorithm for continually running fully recurrent neural network", 1, pp.1989~

관련 논문AI추천

이 간행물의 다른 논문 (13건)