메뉴 건너뛰기




Volumn 56, Issue 5, 2008, Pages 1812-1820

Speech signal enhancement based on MAP algorithm in the ICA space

Author keywords

Generalized Gaussian model; Independent component analysis (ICA); Maximum a posteriori (MAP) estimation; Non Gaussian noise; Sparse code shrinkage; Speech enhancement; Wiener filter

Indexed keywords

GENERALIZED GAUSSIAN MODEL; INDEPENDENT COMPONENT ANALYSIS (ICA); MAXIMUM A POSTERIORI (MAP) ESTIMATION; NON-GAUSSIAN NOISE; SPARSE CODE SHRINKAGE; WIENER FILTER;

EID: 64349087048     PISSN: 1053587X     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSP.2007.910555     Document Type: Article
Times cited : (37)

References (21)
  • 1
    • 0018455310 scopus 로고
    • Suppression of acoustic noise in speech using spectral subtraction
    • Apr
    • S. Boll, "Suppression of acoustic noise in speech using spectral subtraction," IEEE Trans. Acoust., Speech, Signal Process., vol. 27, no. 2, pp. 113-120, Apr. 1979.
    • (1979) IEEE Trans. Acoust., Speech, Signal Process , vol.27 , Issue.2 , pp. 113-120
    • Boll, S.1
  • 2
    • 0032681190 scopus 로고    scopus 로고
    • Adaptive two-band spectral subtraction with multi-window spectral estimation
    • Phoenix, AZ
    • C. He and G. Zweig, "Adaptive two-band spectral subtraction with multi-window spectral estimation," in Proc. Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), Phoenix, AZ, 1999, vol. 2, pp. 793-796.
    • (1999) Proc. Int. Conf. Acoustics, Speech, Signal Processing (ICASSP) , vol.2 , pp. 793-796
    • He, C.1    Zweig, G.2
  • 3
    • 0036293748 scopus 로고    scopus 로고
    • A multi-band spectral subtraction method for enhancing speech corrupted by colored noise
    • Orlando, FL, May
    • S. Kamath and P. Loizou, "A multi-band spectral subtraction method for enhancing speech corrupted by colored noise," in Proc. Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), Orlando, FL, May 2002, vol. 4, pp. 4164-4167.
    • (2002) Proc. Int. Conf. Acoustics, Speech, Signal Processing (ICASSP) , vol.4 , pp. 4164-4167
    • Kamath, S.1    Loizou, P.2
  • 4
    • 0018642851 scopus 로고
    • Enhancement and bandwidth compression of noisy speech
    • J. Lim and A. Oppenheim, "Enhancement and bandwidth compression of noisy speech," Proc. IEEE, vol. 67, pp. 1586-1604, 1979.
    • (1979) Proc. IEEE , vol.67 , pp. 1586-1604
    • Lim, J.1    Oppenheim, A.2
  • 5
    • 0033683501 scopus 로고    scopus 로고
    • Low distortion speech enhancement
    • I. Y. Soon and S. N. Koh, "Low distortion speech enhancement," Proc. Inst. Elec. Eng., vol. 147, no. 3, pp. 247-253, 2000.
    • (2000) Proc. Inst. Elec. Eng , vol.147 , Issue.3 , pp. 247-253
    • Soon, I.Y.1    Koh, S.N.2
  • 6
    • 0348223982 scopus 로고    scopus 로고
    • Sparse code shrinkage: Denoising of nonGaussian data by maximum likelihood estimation
    • A. Hyvarinen, "Sparse code shrinkage: Denoising of nonGaussian data by maximum likelihood estimation," Neural Computat., vol. 11, no. 7, pp. 1739-1768, 1999.
    • (1999) Neural Computat , vol.11 , Issue.7 , pp. 1739-1768
    • Hyvarinen, A.1
  • 7
    • 0034245955 scopus 로고    scopus 로고
    • Speech enhancement with MAP estimation and ICA-based speech features
    • J.-H. Lee, H.-Y. Jung, T.-W. Lee, and S.-Y. Lee, "Speech enhancement with MAP estimation and ICA-based speech features," Electron. Lett. vol. 36, pp. 1506-1507, 2000.
    • (2000) Electron. Lett , vol.36 , pp. 1506-1507
    • Lee, J.-H.1    Jung, H.-Y.2    Lee, T.-W.3    Lee, S.-Y.4
  • 8
    • 0034849095 scopus 로고    scopus 로고
    • I. Potamitis, N. Fakotakis, G. Kokkinakis, and, Speech enhancement using the sparse code shrinkage technique, in Proc. Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), Salt Lake City, UT, 2001, pp. 621-624.
    • I. Potamitis, N. Fakotakis, G. Kokkinakis, and, "Speech enhancement using the sparse code shrinkage technique," in Proc. Int. Conf. Acoustics, Speech, Signal Processing (ICASSP), Salt Lake City, UT, 2001, pp. 621-624.
  • 9
    • 0036821339 scopus 로고    scopus 로고
    • SAR speckle reduction using wavelet denoising and Markov random field modeling
    • H. Xie, L. E. Pierce, and F. T. Ulaby, "SAR speckle reduction using wavelet denoising and Markov random field modeling," IEEE Trans. Geosci. Remote Sens., vol. 40, no. 10, pp. 2196-2212, 2002.
    • (2002) IEEE Trans. Geosci. Remote Sens , vol.40 , Issue.10 , pp. 2196-2212
    • Xie, H.1    Pierce, L.E.2    Ulaby, F.T.3
  • 10
    • 64349105368 scopus 로고    scopus 로고
    • Bayesian single channel speech enhancement exploiting sparseness in the ICA domain
    • presented at the, Vienna, Austria, Sep. 6-10
    • L. Hong, J. Rosca, and R. Balan, "Bayesian single channel speech enhancement exploiting sparseness in the ICA domain," presented at the Eur. Signal Process. Conf. (EUSIPCO), Vienna, Austria, Sep. 6-10, 2004.
    • (2004) Eur. Signal Process. Conf. (EUSIPCO)
    • Hong, L.1    Rosca, J.2    Balan, R.3
  • 11
    • 27644552178 scopus 로고    scopus 로고
    • Speech enhancement employing Laplacian-Gaussian mixture
    • Sep
    • S. Gazor and W. Zhang, "Speech enhancement employing Laplacian-Gaussian mixture," IEEE Trans. Speech Audio Process., vol. 13, no. 5, pp. 896-904, Sep. 2005.
    • (2005) IEEE Trans. Speech Audio Process , vol.13 , Issue.5 , pp. 896-904
    • Gazor, S.1    Zhang, W.2
  • 12
    • 22944438092 scopus 로고    scopus 로고
    • Speech enhancement by MAP spectral amplitude estimation using a super-Gaussian speech model
    • T. Letter and P. Vary, "Speech enhancement by MAP spectral amplitude estimation using a super-Gaussian speech model," EURASIP J. Appl. Signal Process., pp. 1110-1126, 2005.
    • (2005) EURASIP J. Appl. Signal Process , pp. 1110-1126
    • Letter, T.1    Vary, P.2
  • 13
    • 0141702133 scopus 로고    scopus 로고
    • MMSE estimation of magnitude-squared DFT coefficients with super-Gaussian priors
    • Hong Kong, China, Apr
    • C. Breithaupt and R. Martin, "MMSE estimation of magnitude-squared DFT coefficients with super-Gaussian priors," in Proc. Int. Conf. Acoustics, Speech, Signal Process. (ICASSP), Hong Kong, China, Apr. 2003, vol. 1, pp. 896-899.
    • (2003) Proc. Int. Conf. Acoustics, Speech, Signal Process. (ICASSP) , vol.1 , pp. 896-899
    • Breithaupt, C.1    Martin, R.2
  • 15
    • 0031122399 scopus 로고    scopus 로고
    • Infomax and maximum likelihood for blind source separation
    • Apr
    • J.-F. Cardoso, "Infomax and maximum likelihood for blind source separation," IEEE Signal Process. Lett., vol. 4, no. 4, pp. 112-114, Apr. 1997.
    • (1997) IEEE Signal Process. Lett , vol.4 , Issue.4 , pp. 112-114
    • Cardoso, J.-F.1
  • 16
    • 84862602919 scopus 로고    scopus 로고
    • The effectiveness of ICA-based representation: Application to speech feature extraction for noise robust speaker recognition
    • presented at the, Florence, Italy, Sep. 4-8
    • X. Zou, P. Jancovic, and J. Liu, "The effectiveness of ICA-based representation: Application to speech feature extraction for noise robust speaker recognition," presented at the Eur. Signal Process. Conf. (EUSIPCO), Florence, Italy, Sep. 4-8, 2006.
    • (2006) Eur. Signal Process. Conf. (EUSIPCO)
    • Zou, X.1    Jancovic, P.2    Liu, J.3
  • 18
    • 0032612381 scopus 로고    scopus 로고
    • High-order constrasts for independent component analysis
    • J.-F. Cardoso, "High-order constrasts for independent component analysis," Neural Computat., vol. 11, no. 1, pp. 157-192, 1999.
    • (1999) Neural Computat , vol.11 , Issue.1 , pp. 157-192
    • Cardoso, J.-F.1
  • 20
    • 0002792873 scopus 로고    scopus 로고
    • Global optimization using the DIRECT algorithm in Matlab
    • B. Mattias and H. Kenneth, "Global optimization using the DIRECT algorithm in Matlab," Adv. Model. Optimiz., vol. 1, no. 2, 1999.
    • (1999) Adv. Model. Optimiz , vol.1 , Issue.2
    • Mattias, B.1    Kenneth, H.2
  • 21
    • 0029307534 scopus 로고
    • De-noising by soft-thresholding
    • D. Donoho, "De-noising by soft-thresholding," IEEE Trans. Inf. Theory, vol. 43, no. 3, pp. 613-627, 1995.
    • (1995) IEEE Trans. Inf. Theory , vol.43 , Issue.3 , pp. 613-627
    • Donoho, D.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.