$\require{mediawiki-texvc}$

연합인증

연합인증 가입 기관의 연구자들은 소속기관의 인증정보(ID와 암호)를 이용해 다른 대학, 연구기관, 서비스 공급자의 다양한 온라인 자원과 연구 데이터를 이용할 수 있습니다.

이는 여행자가 자국에서 발행 받은 여권으로 세계 각국을 자유롭게 여행할 수 있는 것과 같습니다.

연합인증으로 이용이 가능한 서비스는 NTIS, DataON, Edison, Kafe, Webinar 등이 있습니다.

한번의 인증절차만으로 연합인증 가입 서비스에 추가 로그인 없이 이용이 가능합니다.

다만, 연합인증을 위해서는 최초 1회만 인증 절차가 필요합니다. (회원이 아닐 경우 회원 가입이 필요합니다.)

연합인증 절차는 다음과 같습니다.

최초이용시에는
ScienceON에 로그인 → 연합인증 서비스 접속 → 로그인 (본인 확인 또는 회원가입) → 서비스 이용

그 이후에는
ScienceON 로그인 → 연합인증 서비스 접속 → 서비스 이용

연합인증을 활용하시면 KISTI가 제공하는 다양한 서비스를 편리하게 이용하실 수 있습니다.

Efficient Noise Estimation for Speech Enhancement in Wavelet Packet Transform 원문보기

The journal of the Acoustical Society of Korea, v.25 no.4E, 2006년, pp.154 - 158  

Jung, Sung-Il (School of Electrical and Computer Engineering, Hanyang University) ,  Yang, Sung-Il (School of Electrical and Computer Engineering, Hanyang University)

Abstract ▼ AI-Helper 아이콘AI-Helper

In this paper, we suggest a noise estimation method for speech enhancement in nonstationary noisy environments. The proposed method consists of the following two main processes. First, in order to receive fewer affect of variable signals, a best fitting regression line is used, which is obtained by ...

주제어

#Noise estimation   #Speech enhancement   #Best fitting regression line   #Uniform wavelet packet transform   #Differential forgetting factor   #Correlation coefficient  

AI 본문요약
AI-Helper 아이콘 AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

제안 방법

  • 05. For the experiment, 20 speech signals consisting of 10 female and 10 male speakers are chosen from TIMIT database, and 2 types of noise are selected from NoiseX-92 database: speech-like noise and aircraft cockpit noise, Each speech is corrupted by each type noises with SNR 0 dB, 5 dB, and 10 dB. The sampling frequency is 16 kHz.
  • In this paper, we present an efficient noise estimation method by using the estimated noise at the previous frame only, without employing the statistical information of long past frames and nonspeech frames obtained by the VAD. First, in order to receive fewer affect of variable signals, the best fitting regression line (BFRL) [11] is used, which is calculated by applying the least squares method to coefficient magnitudes in the node with the uniform wavelet packet transform (UWPT) [13].

이론/모형

  • In this paper, we present an efficient noise estimation method by using the estimated noise at the previous frame only, without employing the statistical information of long past frames and nonspeech frames obtained by the VAD. First, in order to receive fewer affect of variable signals, the best fitting regression line (BFRL) [11] is used, which is calculated by applying the least squares method to coefficient magnitudes in the node with the uniform wavelet packet transform (UWPT) [13]. Next, in order to update the noise estimation efficiently, the differential forgetting factor and the correlation coefficient per subband are used, where subband is employed for applying the weighted value according to the change of signals.
본문요약 정보가 도움이 되었나요?

참고문헌 (14)

  1. B. Carnero and A. Drygajlo, 'Perceptual speech coding and enhancement using frame-synchronized fast wavelet packet transform algorithm,' IEEE Trans. Signal Processing, 47(6) 1622-1635, Jun. 1999 

    상세보기 crossref

  2. S. F. Boll, 'Suppression of acoustic noise in speech using spectral subtraction,' IEEE Trans. Acoustic Speech Signal Processing, vol, ASSP-27, 2 113-120, Apr. 1979 

  3. N. Virag, 'Single channel speech enhancement based on masking properties of the human auditory system,' IEEE Trans. Speech and Audio Processing, 7(2) 126-137, Mar. 1999 

    상세보기 crossref

  4. R. Martin, 'Spectral subtraction based on minimum statistics, 'EUROSPEECH, 1182-1185, Sept. 1994 

  5. G. Doblinger, 'Computationally efficient speech enhancement by spectral minima tracking in subbands,' EUROSPEECH, 1513-1516, Sept. 1995 

  6. I. Cohen and B. Berdugo, 'Noise estimation by minima controlled recursive averaging for robust speech enhancement,' IEEE Signal Process. Lett., 9(1) 12-15, Jan. 2002 

    상세보기 crossref

  7. I. Cohen, 'Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging,' IEEE Trans. Speech and Audio Processing, 11(5) 466-475, Sept. 2003 

    상세보기 crossref

  8. S. Rangachari, P. C. Loizou, and Y. Hu, 'A noise estimation algorithm with rapid adaptation for highly non-stationary environments,' IEEE ICASSP, 305-308, May 2004 

  9. Z. Lin and R. Goubran, 'Instant noise estimation using Fourier transform of AMDF and variable start minima search,' IEEE ICASSP, 161-164, Mar. 2005 

  10. H. G. Hirsh and C. Ehrlicher, 'Noise estimation techniques for robust speech recognition,' IEEE ICASSP, 153-156, May 1995 

  11. T. K. Moon and W. C. Stirling, Mathematical methods and algorithms for signal processing, Upper Saddle River, (NJ: PrenticeHall, 2000) 

  12. J. R. Deller, J. G. Proakis, and J. H. L. Hansen, Discrete-time processing of speech signals, Englewood Cliffs, (NJ: Prentice-Hall, 1993) 

  13. S. Mallat, A wavelet tour of signal processing, (2nd Ed., Academic Press, 1999) 

  14. N. Virag, 'Single channel speech enhancement based on masking properties of the human auditory system,' IEEE Trans. Speech Audio Processing, 7(2) 126-137, Mar. 1999 

    상세보기 crossref

저자의 다른 논문 :

관련 콘텐츠

저작권 관리 안내
섹션별 컨텐츠 바로가기

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

AI-Helper 아이콘
AI-Helper
안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

선택된 텍스트

맨위로