메뉴 건너뛰기




Volumn 19, Issue 1, 2011, Pages 123-137

Advances in missing feature techniques for robust large-vocabulary continuous speech recognition

Author keywords

Automatic speech recognition (ASR); channel compensation; missing data techniques; noise robustness

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; BINARY MASKS; CEPSTRAL DOMAIN; CHANNEL COMPENSATION; FEATURE DOMAIN; GAUSSIANS; HARD DECISIONS; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; LINEAR TRANSFORM; LOG-SPECTRAL DOMAIN; MISSING DATA TECHNIQUES; MISSING FEATURE THEORIES; NOISE ROBUSTNESS; NOISY DATA; RECOGNITION PERFORMANCE; RECOGNITION PROCESS; SOFT DECISION; STATIC AND DYNAMIC; STRUCTURED COVARIANCE;

EID: 77957739976     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2010.2045235     Document Type: Article
Times cited : (28)

References (42)
  • 3
    • 85032752225 scopus 로고    scopus 로고
    • Robust automatic speech recognition with missing and unreliable acoustic data
    • B. Raj and R. Stern, "Robust automatic speech recognition with missing and unreliable acoustic data", Signal Process. Mag., vol. 22, no. 2, pp. 101-116, 2005.
    • (2005) Signal Process. Mag. , vol.22 , Issue.2 , pp. 101-116
    • Raj, B.1    Stern, R.2
  • 4
    • 0025041264 scopus 로고
    • Perceptual linear predictive (PLP) analysis of speech
    • Apr
    • H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech", J. Acoust. Soc. Amer., vol. 87, no. 4, pp. 1738-1752, Apr. 1990.
    • (1990) J. Acoust. Soc. Amer. , vol.87 , Issue.4 , pp. 1738-1752
    • Hermansky, H.1
  • 5
    • 85135377175 scopus 로고
    • Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP)
    • Genua, Italy, Sep
    • H. Hermansky, N. Morgan, A. Bayya, and P. Kohn, "Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP)", in Proc. Eurospeech, Genua, Italy, Sep. 1991, pp. 1367-1370.
    • (1991) Proc. Eurospeech , pp. 1367-1370
    • Hermansky, H.1    Morgan, N.2    Bayya, A.3    Kohn, P.4
  • 6
    • 0027622158 scopus 로고
    • Root cepstral analysis: A unified view. Application to speech processing in car noise environments
    • Jul
    • P. Alexandre and P. Lockwood, "Root cepstral analysis: A unified view. Application to speech processing in car noise environments", Speech Commun., vol. 12, no. 3, pp. 277-288, Jul. 1993.
    • (1993) Speech Commun. , vol.12 , Issue.3 , pp. 277-288
    • Alexandre, P.1    Lockwood, P.2
  • 7
    • 0032136330 scopus 로고    scopus 로고
    • Robust speech recognition using the modulation spectrogram
    • Aug
    • B. Kingsbury, N. Morgan, and S. Greenberg, "Robust speech recognition using the modulation spectrogram", Speech Commun., vol. 25, pp. 117-132, Aug. 1998.
    • (1998) Speech Commun. , vol.25 , pp. 117-132
    • Kingsbury, B.1    Morgan, N.2    Greenberg, S.3
  • 8
    • 0005451715 scopus 로고    scopus 로고
    • Modelling the recognition of spectrally reduced speech
    • J. Barker and M. Cooke, "Modelling the recognition of spectrally reduced speech", in Proc. Eurospeech, 1997, pp. 2127-2130.
    • (1997) Proc. Eurospeech , pp. 2127-2130
    • Barker, J.1    Cooke, M.2
  • 9
    • 0019053271 scopus 로고
    • Comparison of parametric representations for monosyllabic word recognitions in continuously spoken sentences
    • Aug
    • S. Davis and P. Mermelstein, "Comparison of parametric representations for monosyllabic word recognitions in continuously spoken sentences", IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-28, no. 4, pp. 357-366, Aug. 1980.
    • (1980) IEEE Trans. Acoust., Speech, Signal Process. , vol.ASSP-28 , Issue.4 , pp. 357-366
    • Davis, S.1    Mermelstein, P.2
  • 10
    • 0018455310 scopus 로고
    • Suppression of acoustic noise in speech using spectral subtraction
    • 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. (Pubitemid 9467471)
    • (1979) IEEE Trans Acoust Speech Signal Process , vol.ASSP-27 , Issue.2 , pp. 113-120
    • Boll Steven, F.1
  • 11
    • 85135369853 scopus 로고
    • Noise-adaptive hidden Markov models based on Wiener filters
    • S. V. Vaseghi and B. P. Milner, "Noise-adaptive hidden Markov models based on Wiener filters", in Proc. Eurospeech, 1993, pp. 1023-1026.
    • (1993) Proc. Eurospeech , pp. 1023-1026
    • Vaseghi, S.V.1    Milner, B.P.2
  • 12
    • 0021645331 scopus 로고
    • Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator
    • Dec
    • Y. Ephraim and D. Malah, "Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator", IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-32, no. 6, pp. 1109-1121, Dec. 1984.
    • (1984) IEEE Trans. Acoust., Speech, Signal Process. , vol.ASSP-32 , Issue.6 , pp. 1109-1121
    • Ephraim, Y.1    Malah, D.2
  • 14
    • 0029345417 scopus 로고
    • A signal subspace approach for speech enhancement
    • Jul
    • Y. Ephraim and H. Van Trees, "A signal subspace approach for speech enhancement", IEEE Trans. Speech Audio Process., vol. 3, no. 4, pp. 251-266, Jul. 1995.
    • (1995) IEEE Trans. Speech Audio Process. , vol.3 , Issue.4 , pp. 251-266
    • Ephraim, Y.1    Van Trees, H.2
  • 16
    • 0029725301 scopus 로고    scopus 로고
    • A vector Taylor series approach for environment-independent speech recognition
    • Atlanta, GA, May
    • P. Moreno, B. Raj, and R. Stern, "A vector Taylor series approach for environment-independent speech recognition", in Proc. ICASSP, Atlanta, GA, May 1996, pp. 733-736.
    • (1996) Proc. ICASSP , pp. 733-736
    • Moreno, P.1    Raj, B.2    Stern, R.3
  • 17
    • 0025681008 scopus 로고
    • Hidden Markov model decomposition of speech and noise
    • Albuquerque, NM, Apr
    • A. Varga and R. Moore, "Hidden Markov model decomposition of speech and noise", in Proc. ICASSP, Albuquerque, NM, Apr. 1990, pp. 845-848.
    • (1990) Proc. ICASSP , pp. 845-848
    • Varga, A.1    Moore, R.2
  • 19
    • 0029288633 scopus 로고
    • Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models
    • Apr
    • C. Leggetter and P. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models", Comput. Speech Lang., vol. 9, no. 2, pp. 171-185, Apr. 1995.
    • (1995) Comput. Speech Lang. , vol.9 , Issue.2 , pp. 171-185
    • Leggetter, C.1    Woodland, P.2
  • 20
    • 0028419019 scopus 로고
    • Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains
    • Apr
    • J.-L. Gauvain and C.-H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains", IEEE Trans. Speech Audio Process., vol. 2, no. 2, pp. 291-298, Apr. 1994.
    • (1994) IEEE Trans. Speech Audio Process. , vol.2 , Issue.2 , pp. 291-298
    • Gauvain, J.-L.1    Lee, C.-H.2
  • 21
    • 0035342414 scopus 로고    scopus 로고
    • Robust automatic speech recognition with missing and unreliable acoustic data
    • M. Cooke, P. Green, L. Josifovski, and A. Vizinho, "Robust automatic speech recognition with missing and unreliable acoustic data", Speech Commun., vol. 34, pp. 267-285, 2001.
    • (2001) Speech Commun. , vol.34 , pp. 267-285
    • Cooke, M.1    Green, P.2    Josifovski, L.3    Vizinho, A.4
  • 22
    • 11144316019 scopus 로고    scopus 로고
    • Decoding speech in the presence of other sources
    • J. Barker, M. Cooke, and D. Ellis, "Decoding speech in the presence of other sources", Speech Commun., vol. 45, no. 1, pp. 5-25, 2005.
    • (2005) Speech Commun. , vol.45 , Issue.1 , pp. 5-25
    • Barker, J.1    Cooke, M.2    Ellis, D.3
  • 23
    • 0037841203 scopus 로고    scopus 로고
    • State based imputation of missing data for robust speech recognition and speech enhancement
    • Budapest, Hungary
    • L. Josifovski, M. Cooke, P. Green, and A. Vizinho, "State based imputation of missing data for robust speech recognition and speech enhancement", in Proc. Eurospeech, Budapest, Hungary, 1999, pp. 2837-2840.
    • (1999) Proc. Eurospeech , pp. 2837-2840
    • Josifovski, L.1    Cooke, M.2    Green, P.3    Vizinho, A.4
  • 24
    • 4644336054 scopus 로고    scopus 로고
    • Reconstruction of missing features for robust speech recognition
    • B. Raj, M. L. Seltzer, and R. Stern, "Reconstruction of missing features for robust speech recognition", Speech Commun., vol. 43, no. 4, pp. 275-296, 2004.
    • (2004) Speech Commun. , vol.43 , Issue.4 , pp. 275-296
    • Raj, B.1    Seltzer, M.L.2    Stern, R.3
  • 25
    • 85009212472 scopus 로고    scopus 로고
    • Robust speech recognition using missing feature theory in the cepstral or LDA domain
    • Geneva, Switzerland, Sep
    • H. Van Hamme, "Robust speech recognition using missing feature theory in the cepstral or LDA domain", in Proc. Eurospeech, Geneva, Switzerland, Sep. 2003, pp. 3089-3092.
    • (2003) Proc. Eurospeech , pp. 3089-3092
    • Van Hamme, H.1
  • 26
    • 85009128803 scopus 로고    scopus 로고
    • PROSPECT features and their application to missing data techniques for robust speech recognition
    • Jeju Island, Korea
    • H. Van Hamme, "PROSPECT features and their application to missing data techniques for robust speech recognition", in Proc. Interspeech, Jeju Island, Korea, 2004, pp. 101-104.
    • (2004) Proc. Interspeech , pp. 101-104
    • Van Hamme, H.1
  • 27
    • 0000540156 scopus 로고    scopus 로고
    • Soft decisions in missing data techniques for robust automatic speech recognition
    • Beijing, China, Sep
    • J. Barker, L. Josifovski, M. Cooke, and P. Green, "Soft decisions in missing data techniques for robust automatic speech recognition", in Proc. Interspeech, Beijing, China, Sep. 2000, pp. 373-376.
    • (2000) Proc. Interspeech , pp. 373-376
    • Barker, J.1    Josifovski, L.2    Cooke, M.3    Green, P.4
  • 28
    • 18744390181 scopus 로고    scopus 로고
    • From missing data to maybe useful data: Soft data modelling for noise robust ASR
    • Stratford-upon-Avon, U. K., Apr
    • A. Morris, J. Barker, and H. Bourlard, "From missing data to maybe useful data: Soft data modelling for noise robust ASR", in Proc. WISP-01, Stratford-upon-Avon, U. K., Apr. 2001, pp. 153-164.
    • (2001) Proc. WISP-01 , pp. 153-164
    • Morris, A.1    Barker, J.2    Bourlard, H.3
  • 29
    • 70349226857 scopus 로고    scopus 로고
    • Bounded conditional mean imputation with Gaussian mixture models: A reconstruction approach to partly occluded features
    • Taipei, Taiwan, Sep
    • F. Faubel, J. McDonough, and D. Klakow, "Bounded conditional mean imputation with Gaussian mixture models: A reconstruction approach to partly occluded features", in Proc. ICASSP, Taipei, Taiwan, Sep. 2009, pp. 3869-3872.
    • (2009) Proc. ICASSP , pp. 3869-3872
    • Faubel, F.1    McDonough, J.2    Klakow, D.3
  • 30
    • 51449106172 scopus 로고    scopus 로고
    • Robust speech recognition using missing data techniques in the prospect domain and fuzzy masks
    • Las Vegas, NV, Apr
    • M. Van Segbroeck and H. Van Hamme, "Robust speech recognition using missing data techniques in the prospect domain and fuzzy masks", in Proc. ICASSP, Las Vegas, NV, Apr. 2008, pp. 4393-4396.
    • (2008) Proc. ICASSP , pp. 4393-4396
    • Van Segbroeck, M.1    Van Hamme, H.2
  • 31
    • 44949096514 scopus 로고    scopus 로고
    • Handling convolutional noise in missing data automatic speech recognition
    • Pittsburgh, PA, Sep
    • M. Van Segbroeck and H. Van Hamme, "Handling convolutional noise in missing data automatic speech recognition", in Proc. Interspeech, Pittsburgh, PA, Sep. 2006, pp. 2526-2565.
    • (2006) Proc. Interspeech , pp. 2526-2565
    • Van Segbroeck, M.1    Van Hamme, H.2
  • 32
    • 13344250769 scopus 로고    scopus 로고
    • Missing feature theory and probabilistic estimation of clean speech components for robust speech recognition
    • Budapest, Hungary
    • P. Reneveyand A. Drygajlo, "Missing feature theory and probabilistic estimation of clean speech components for robust speech recognition", in Proc. Eurospeech, Budapest, Hungary, 1999, pp. 2627-2630.
    • (1999) Proc. Eurospeech , pp. 2627-2630
    • Reneveyand, P.1    Drygajlo, A.2
  • 33
    • 4644317224 scopus 로고    scopus 로고
    • A Bayesian classifier for spectrographic mask estimation for missing feature speech recognition
    • M. L. Seltzer, B. Raj, and R. Stern, "A Bayesian classifier for spectrographic mask estimation for missing feature speech recognition", Speech Commun., vol. 43, no. 4, pp. 379-393, 2004.
    • (2004) Speech Commun. , vol.43 , Issue.4 , pp. 379-393
    • Seltzer, M.L.1    Raj, B.2    Stern, R.3
  • 34
    • 33947622695 scopus 로고    scopus 로고
    • Handling time-derivative features in a missing data framework for robust automatic speech recognition
    • Toulouse, France, May
    • H. Van Hamme, "Handling time-derivative features in a missing data framework for robust automatic speech recognition", in Proc. ICASSP, Toulouse, France, May 2006, pp. 293-296.
    • (2006) Proc. ICASSP , pp. 293-296
    • Van Hamme, H.1
  • 35
    • 70450167189 scopus 로고    scopus 로고
    • Vector-quantization based mask estimation for missing data automatic speech recognition
    • Antwerp, Belgium, Aug
    • M. Van Segbroeck and H. Van Hamme, "Vector-Quantization based mask estimation for missing data automatic speech recognition", in Proc. Interspeech, Antwerp, Belgium, Aug. 2007, pp. 910-913.
    • (2007) Proc. Interspeech , pp. 910-913
    • Van Segbroeck, M.1    Van Hamme, H.2
  • 36
    • 85009074922 scopus 로고    scopus 로고
    • Harmonic tunneling: Tracking nonstationary noises during speech
    • Aalborg, Denmark, Sep
    • D. Ealey, H. Kelleher, and D. Pearce, "Harmonic tunneling: Tracking nonstationary noises during speech", in Proc. Eurospeech, Aalborg, Denmark, Sep. 1999, pp. 437-410.
    • (1999) Proc. Eurospeech , pp. 437-410
    • Ealey, D.1    Kelleher, H.2    Pearce, D.3
  • 37
    • 33847629729 scopus 로고    scopus 로고
    • On noise masking for automatic missing data speech recognition: Asurveyand discussion
    • Jul
    • C. Cerisara, S. Demange, and J.-P. Haton, "On noise masking for automatic missing data speech recognition: Asurveyand discussion", Computer, Speech, Lang., vol. 21, no. 3, pp. 443-457, Jul. 2007.
    • (2007) Computer, Speech, Lang. , vol.21 , Issue.3 , pp. 443-457
    • Cerisara, C.1    Demange, S.2    Haton, J.-P.3
  • 38
    • 2942539074 scopus 로고    scopus 로고
    • Techniques for handling convolutional distortion with 'missing data' automatic speech recognition
    • K. Palomäki, G. Brown, and J. Barker, "Techniques for handling convolutional distortion with 'missing data' automatic speech recognition", Speech Commun., vol. 43, no. 1-2, pp. 123-142, 2004.
    • (2004) Speech Commun. , vol.43 , Issue.1-2 , pp. 123-142
    • Palomäki, K.1    Brown, G.2    Barker, J.3
  • 40
    • 85009227702 scopus 로고    scopus 로고
    • Analysis of the aurora large vocabulary evaluations
    • Geneva, Switzerland, Sep
    • N. Parihar and J. Picone, "Analysis of the aurora large vocabulary evaluations", in Proc. Eurospeech, Geneva, Switzerland, Sep. 2003, pp. 337-340.
    • (2003) Proc. Eurospeech , pp. 337-340
    • Parihar, N.1    Picone, J.2
  • 41
    • 77957726993 scopus 로고    scopus 로고
    • Group Online. Available
    • "ESAT-PSI Speech", Group [Online]. Available: http://www.esat. kuleuven. be/psi/spraak
    • ESAT-PSI Speech


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.