한국음향학회지 (The Journal of the Acoustical Society of Korea)

  • 제32권3호
  • /
  • Pages.269-278
  • /
  • 2013
  • /
  • 1225-4428(pISSN)
  • /
  • 2287-3775(eISSN)
한국음향학회 (The Acoustical Society of Korea)
권호 표지
DOI QR코드

DOI QR Code

국가기록원 음성 기록물의 복원과 분석

Restoration for Speech Records Managed by the National Archives of Korea

  • 오세진 (연세대학교 전기전자공학과) ;
  • 강홍구 (연세대학교 전기전자공학과)
  • 투고 : 2012.12.03
  • 심사 : 2012.12.28
  • 발행 : 2013.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

국가기록원의 음성 기록물은 우리나라의 근현대사를 담은 중요한 기록물이다. 하지만 아날로그로 녹음된 방식은 시간이 지남에 따라 손실을 피할 수 없어 디지털로 변환하여 관리 및 서비스할 필요성이 있다. 그에 따라 왜곡이 발생한 부분에 대해 본래의 정보를 복원하는 작업은 매우 중요하며, 본 논문은 음성 기록물의 훼손 종류에 따라 4가지의 카테고리로 분류하고 음량, 정상 잡음, 돌발 잡음에 맞는 복원 알고리즘을 적용하였다. 그 결과 음량은 음성 존재구간에 대해서 -26 dBov로 조정했고 SNR은 10 dB이상 상승하였다. 특히 기존에는 음성이 훼손된 부분을 순차적으로 청취하여 개별적으로 문제를 해결해야 했기 때문에 방대한 자료를 복원하기는 불가능 했지만 자동 복원 알고리즘을 도입하여 보다 효율적인 방식으로 복원할 수 있게 되었다.

The speech recording of the National Archives of Korea contains very important traces which represent modern times of Korea. But the way to be recorded by analogue is easily contaminated as time goes by. So it has to be digitalized for management and services. Consequently, restoration method of distorted speech is needed. We propose the four classes for each distortion kind and apply restoration algorithms for the cases of speech level, stationary noise and abrupt noise. As a result, speech volume adjusts to -26 dBov for only on the speech region and SNR improves above 10dB. Especially, conventional way to remove the noise is almost impossible because we need to listen to all of them but it can be more effective by adaptation of auto restoration algorithm.

키워드

참고문헌

  1. iZotopeRX, audio repair toolkit http://www.izotope.com/ products/audio/rx/.
  2. Y. Ephraim and D. Malah, "Speech enhancement using a minimum mean-square error log-spectral amplitude estimator," IEEE Trans. on Acoust., Speech and Signal Process. 33, 443-445 (1985). https://doi.org/10.1109/TASSP.1985.1164550
  3. I. Cohen and B. Berdugo, "Speech enhancement for nonstationary noise environments," Signal Process., 81, 2401-4218, (2001).
  4. S. V. Vaseghi, Advanced digital signal processing and noise reduction, 2nd ed. (John Wiley & Sons, UK, 2000).
  5. T. Kasparis and J. Lane, "Suppression of impulsive disturbances from audio signals," Electronics letters, 29, 1926-1927 (1993). https://doi.org/10.1049/el:19931282
  6. A. J. Efron and H. Jeen, "Detection in impulsive noise based on robust whitening," IEEE Trans. on Signal Process.42, 1572-1576 (1994). https://doi.org/10.1109/78.286980
  7. S. R. Kim and A. Efron, "Adaptive robust impulse noise filtering," IEEE Trans. on Signal Process.43, 1855-1866 (1995). https://doi.org/10.1109/78.403344
  8. I. Kauppinen, "Methods for detecting impulsive noise in speech and audio signals," in Proc. IEEE Int Conf. on Digital Signal Process.2, 967-970 (2002).
  9. T. F. Quatieri, Discrete-time speech signal processing, (Prentice Hall, New Jersey, 2001).
  10. J. Beh, K. Kim and H. Ko, "Noise estimation for robust speech enhancement in transient noise environment," in Proc. KSCSP 2007, 24, 35-36 ( 2007).
  11. ITU-T, ITU-T recommendation P. 56, ITU-T, 2011.
  12. M. S. Kim, H. S. Sin, H. G. Kang, "Time-Frequency Domain Impulsive Noise Detection System in Speech Signal" (in Korean), J. Acoust. Soc. Kr. Suppl. 2(s) 30, 73-79 (2011). https://doi.org/10.7776/ASK.2011.30.2.073
  13. ITU-T, ITU-T recommendation G. 729, ITU-T, 1996.
  14. A. M. Kondoz, Digital speech-coding for low bit rate communication systems, (John wiley & sons, England, 1994).
  15. M. Choi and H. Kang, "Transient noise reduction in speech signal with a modified long-term predictor," EURASIP Journal on Advances in Signal Processing (2011).
  16. Y. H. Son, Y. S. Park, H. S. Ahn, S. M. Lee, "An Improved Speech Absence Probability Estimation based on Environmental Noise Classification" (in Korean), J. Acoust. Soc. Kr. Suppl. 7(s) 30, 383-389 (2011). https://doi.org/10.7776/ASK.2011.30.7.383
  17. Y. G. Kim, H. J. Song, H. S. Kim, "Simultaneous Speaker and Environment Adaptation by Environment Clustering in Various Noise Environments" (in Korean), J. Acoust. Soc. Kr. Suppl. 6(s) 28, 566-571 (2009).