텔레매틱스 시스템을 위한 반향제거 및 Barge-In 기능을 갖는 음성인터페이스

Speech Interface with Echo Canceller and Barge- In Functionality for Telematic System

  • 김준 (국방과학구소 무인자율화 연구실) ;
  • 배건성 (경북대학교 전자전기컴퓨터학부)
  • 발행 : 2009.07.31

초록

본 논문에서는 배경잡음과 반향이 존재하는 차량환경에서 음성인식 성능을 향상시키기 위해 상관계수를 이용한 동시통화 검출 알고리즘을 적용한 음향 반향제거기와 barge-in 기능을 갖는 음성 인터페이스를 구현하였다. 상관계수를 이용한 동시통화 검출 알고리즘은 임계치 설정 및 배경잡음의 영향 등으로 인해 검출 오류가 발생한다. 이를 보완하기 위해 동시통화 검출 조건으로 매 샘플마다 입력신호에서 추정한 배경잡음 및 반향신호의 평균 전력을 이용하여 동시통화 검출 오류를 줄였으며, 시변의 임계치를 적용한 후처리 단을 통해 시변의 잔여 잡음 성분을 제거하였다. 또한 안내음성 중에 음성입력이 가능하도록 barge-in 기능을 적용한 음성 인터페이스 시스템을 구현하였다. 제안한 음성 인터페이스 시스템은 동시통화 검출 오류와 이로 인해 발생되는 문제점을 효율적으로 해결할 수 있음을 실험을 통하여 확인하였다.

In this paper, we develop a speech interface that has acoustic echo cancelling and barge-in functionalities in the car environment. In the echo canceller, DT (Double-Talk) detection algorithm using the correlation coefficients between reference and desired signals can make DT detection errors often in the background noise. We reduce the DT detection errors by using the average power of noise and echo estimated from the input signal. In addition, to make it possible for drivers to give speech command to the system by interrupting the speaker output, barge-in functionality is implemented with the combination of DT detection and appropriate gain control of the speaker output. Through the computer simulation with the assumed car environment and experiment in the real laboratory environment, implemented speech interface has shown good performance in removing acoustic echo signals in the noisy environment with proper operation of barge-in functionality.

키워드

참고문헌

  1. Y. Zhao, "Telematics: sale and fun driving,” Intelligent Systems, IEEE Expert vol. 17 , no. 1 , pp. 10-14, 2002 https://doi.org/10.1109/5254.988442
  2. VOICE RECOGNITION tips for OnStar Personal Calling, http://www.onstar.com/us_english/downloadable/opc_voice_recognition.pdf
  3. S. Haykin, Adaptive Filter Theory, Prentice-Hall, New Jersey, 1996
  4. B. Widrow and S. D. Steams, Adaptive Signal Processing, Prentice-Hall, New Jersey, 1985
  5. D. G. Messerschmit, "Echo Cancellation in Speech and Data Transmission", Selected Areas in Communications, lEEE Journal on, vol. 2, no. 2 , pp. 283-297, 1984 https://doi.org/10.1109/JSAC.1984.1146062
  6. Jae Ha Yoo and Sung Ho Cho, "A New Double Talk Detector Using The Lattice Predictors For An Acoustic Echo Canceller", in Proc. IEEE Conf. TENCON'97, Speech and Image Tech-nologies for Computing and Telecommunications, vol. 2, pp. 483-486, Dec. 1997 https://doi.org/10.1109/TENCON.1997.648250
  7. Hua Ye and Bo-Xiu Wu, "A New Double-Talk Detection Algorithm Based on the Orthogonality Theorem", IEEE Trans, Communications, vol. 39 , no. 11, pp. 1542-1545, 1991 https://doi.org/10.1109/26.111430
  8. 김시호, 권홍석, 배건성, "음향반향제어기에서 보조필터를 이용한 동시통화 검출 성능 개선", 한국음향학회지, 21권, 1호, 249-252쪽, 2002
  9. M. Kallinger and J. Bitzer, "Study on Combining Multi-Channel Echo Cancellers with Beamformers," in Proc. Int. Conf. Acoust, Speech and Signal Processing, ICASSP'00, vol. 2, pp. 797-800, June. 2000 https://doi.org/10.1109/ICASSP.2000.859080
  10. H. Puder and P. Dreiseitel, “Implementation of A Hands-Free Car Phone with Echo Cancellation and Noise Dependent Loss Control”, in Proc. Int. Conf. Acoust, Speech, and Signal Processing, ICASSP’00, vol. 6 ,pp. 3622-3625, June. 2000 https://doi.org/10.1109/ICASSP.2000.860186
  11. Y. Ephraim and D. Malah, "Speech Enhancement Using a Minimum Mean Square Error Short-Time Spectral Amplitude Estimator," IEEE Trans. Acoust. Speech And Signal Processubg, vol.32, no. 6, pp. 1109-1121, 1984 https://doi.org/10.1109/TASSP.1984.1164453
  12. N. Strom and S. Seneff, "Intelligent barge-in in converstional systems" MIT laboratory for Computer Science, Proc. ICSLP, Beijing, China, Oct. 2000
  13. Jont B. Allen and David A. Berkley, "Image method for effi-ciently simulating small-room acoustics", Journal of ASA, Vol. 65, no. 4, pp. 943 - 950, 1979 https://doi.org/10.1121/1.382599