메뉴 건너뛰기




Volumn 15, Issue 3, 2007, Pages 1087-1097

Static and dynamic spectral features: Their noise robustness and optimal weights for ASR

Author keywords

Discriminative training; Dynamic features; Exponential weighting; Noise robustness

Indexed keywords

CANTONESE; CEPSTRUM; CHANNEL DISTORTIONS; CONNECTED DIGITS; DECODING PROCESS; DISCRIMINATIVE TRAINING; DYNAMIC FEATURES; EXPONENTIAL WEIGHTING; FEATURE WEIGHTS; MODEL ADAPTATIONS; NOISE ESTIMATIONS; NOISE LEVELS; NOISE ROBUSTNESS; OPTIMAL WEIGHTS; PERFORMANCE IMPROVEMENTS; SIGNAL-TO-NOISE RATIOS; SPECTRAL FEATURES; STATIC AND DYNAMICS; WORD ERROR RATE REDUCTIONS;

EID: 60849117157     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2006.885932     Document Type: Article
Times cited : (9)

References (28)
  • 2
    • 84928837806 scopus 로고
    • A joint synchrony/mean-rate model of auditory speech processing
    • S. Seneff, "A joint synchrony/mean-rate model of auditory speech processing," J. Phonetics, vol. 16, pp. 55-76, 1988.
    • (1988) J. Phonetics , vol.16 , pp. 55-76
    • Seneff, S.1
  • 3
    • 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, pp. 113-120, 1979.
    • (1979) IEEE Trans. Acoust. Speech, Signal Process , vol.27 , pp. 113-120
    • Boll, S.1
  • 4
    • 0016067897 scopus 로고
    • Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification
    • B. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. Amer., vol. 55, pp. 1304-1312, 1974.
    • (1974) J. Acoust. Soc. Amer , vol.55 , pp. 1304-1312
    • Atal, B.1
  • 5
    • 0030245128 scopus 로고    scopus 로고
    • Robust continuous speech recognition using parallel model combination
    • Sep
    • M. J. F. Gales and S. J. Young, "Robust continuous speech recognition using parallel model combination," IEEE Trans. Acoust., Speech, Signal Process., vol. 4, no. 5, pp. 352-359, Sep. 1996.
    • (1996) IEEE Trans. Acoust., Speech, Signal Process , vol.4 , Issue.5 , pp. 352-359
    • Gales, M.J.F.1    Young, S.J.2
  • 6
    • 0029725301 scopus 로고    scopus 로고
    • A vector Taylor series approach for environment independent speech recognition
    • P. J. Moreno, B. Raj, and R. Stern, "A vector Taylor series approach for environment independent speech recognition," in Proc. ICASSP, 1996, pp. 733-736.
    • (1996) Proc. ICASSP , pp. 733-736
    • Moreno, P.J.1    Raj, B.2    Stern, R.3
  • 7
    • 0040262052 scopus 로고
    • Bayesian learning of G aussian mixture densities for hidden Markov models
    • J. L. Gauvian and C.-H. Lee, "Bayesian learning of G aussian mixture densities for hidden Markov models," in Proc. DARPA Speech Natural Language Workshop, 1991, pp. 272-277.
    • (1991) Proc. DARPA Speech Natural Language Workshop , pp. 272-277
    • Gauvian, J.L.1    Lee, C.-H.2
  • 8
    • 0029288633 scopus 로고
    • Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models
    • Apr
    • C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comput. Speech Lang., vol. 9, pp. 171-185, Apr. 1995.
    • (1995) Comput. Speech Lang , vol.9 , pp. 171-185
    • Leggetter, C.J.1    Woodland, P.C.2
  • 9
    • 0035342414 scopus 로고    scopus 로고
    • Robust automatic speech recognition with missing and unreliable data
    • M. Cooke, P. Green, L. Josifovski, and A. Vizinho, "Robust automatic speech recognition with missing and unreliable 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
  • 10
    • 0022667694 scopus 로고
    • Speaker-independent isolated word recognition using dynamic features of speech spectrum
    • Feb
    • S. Furui, "Speaker-independent isolated word recognition using dynamic features of speech spectrum," IEEE Trans. Acoust. Speech, Signal Process., vol. ASSP-34, no. 1, pp. 52-59, Feb. 1986.
    • (1986) IEEE Trans. Acoust. Speech, Signal Process , vol.ASSP-34 , Issue.1 , pp. 52-59
    • Furui, S.1
  • 11
    • 0024035182 scopus 로고
    • On the use of instantaneous and transitional spectral information in speaker recognition
    • Jun
    • F. K. Soong and A. E. Rosenberg, "On the use of instantaneous and transitional spectral information in speaker recognition," IEEE Trans. Acoust., Speech, Signal Process., vol. 36, no. 3, pp. 871-879, Jun. 1988.
    • (1988) IEEE Trans. Acoust., Speech, Signal Process , vol.36 , Issue.3 , pp. 871-879
    • Soong, F.K.1    Rosenberg, A.E.2
  • 12
    • 85057282838 scopus 로고
    • Learning state-dependent stream weights for multi-codebook HMM speech recognition systems
    • I. Rogina and A.Waibel, "Learning state-dependent stream weights for multi-codebook HMM speech recognition systems," in Proc. ICASSP, 1994, pp. 217-220.
    • (1994) Proc. ICASSP , pp. 217-220
    • Rogina, I.1    Waibel, A.2
  • 13
    • 0030676381 scopus 로고    scopus 로고
    • Maximum likelihood weighting of dynamic speech features for CDHMM speech recognition
    • J. Hernando, "Maximum likelihood weighting of dynamic speech features for CDHMM speech recognition," in Proc. ICASSP, 1997, pp. 1267-1270.
    • (1997) Proc. ICASSP , pp. 1267-1270
    • Hernando, J.1
  • 14
    • 0025681006 scopus 로고
    • Robust speaker-independent word recognition using static, dynamic and acceleration features: Experiments with Lombard and noisy speech
    • B. A. Hanson and T. H. Applebaum, "Robust speaker-independent word recognition using static, dynamic and acceleration features: experiments with Lombard and noisy speech," in Proc. ICASSP, 1990, pp. 857-860.
    • (1990) Proc. ICASSP , pp. 857-860
    • Hanson, B.A.1    Applebaum, T.H.2
  • 15
    • 0038669544 scopus 로고    scopus 로고
    • The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions
    • H. G. Hirsch and D. Pearce, "The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions," in Proc. ISCA ITRW ASR, 2000, pp. 181-188.
    • (2000) Proc. ISCA ITRW ASR , pp. 181-188
    • Hirsch, H.G.1    Pearce, D.2
  • 16
    • 0030638046 scopus 로고    scopus 로고
    • The modulation spectrum in the automatic recognition of speech
    • H. Hermansky, "The modulation spectrum in the automatic recognition of speech," in Proc. ASRU, 1997, pp. 140-147.
    • (1997) Proc. ASRU , pp. 140-147
    • Hermansky, H.1
  • 17
    • 0011823639 scopus 로고
    • Improved speech recognition using high-pass filtering of subband envelopes
    • H. G. Hirsch, P. Meyer, and H. W. Ruhl, "Improved speech recognition using high-pass filtering of subband envelopes," in Proc. EUROSPEECH, 1991, pp. 413-416.
    • (1991) Proc. EUROSPEECH , pp. 413-416
    • Hirsch, H.G.1    Meyer, P.2    Ruhl, H.W.3
  • 18
    • 0034817674 scopus 로고    scopus 로고
    • Time and frequency filtering of filter-bank energies for robust HMM speech recognition
    • C. Nadeu, D. Macho, and J. Hernando, "Time and frequency filtering of filter-bank energies for robust HMM speech recognition," Speech Commun., vol. 34, pp. 93-114, 2001.
    • (2001) Speech Commun , vol.34 , pp. 93-114
    • Nadeu, C.1    Macho, D.2    Hernando, J.3
  • 19
    • 84856269531 scopus 로고    scopus 로고
    • Desired characteristics of modulation spectrum for robust automatic speech recognition
    • N. Kanedera, H. Hermansky, and T. Arai, "Desired characteristics of modulation spectrum for robust automatic speech recognition," in Proc. ICASSP, 1998, pp. 613-616.
    • (1998) Proc. ICASSP , pp. 613-616
    • Kanedera, N.1    Hermansky, H.2    Arai, T.3
  • 20
    • 0027957839 scopus 로고
    • Effect of temporal envelope smearing on speech reception
    • R. Drullman, J. M. Festen, and R. Plomp, "Effect of temporal envelope smearing on speech reception," J. Acoust. Soc. Amer., vol. 95, pp. 1053-1064, 1994.
    • (1994) J. Acoust. Soc. Amer , vol.95 , pp. 1053-1064
    • Drullman, R.1    Festen, J.M.2    Plomp, R.3
  • 21
    • 0028287770 scopus 로고
    • Effect of reducing slow temporal modulations on speech reception
    • -, "Effect of reducing slow temporal modulations on speech reception," J. Acoust. Soc. Amer., vol. 95, pp. 2670-2680, 1994.
    • (1994) J. Acoust. Soc. Amer , vol.95 , pp. 2670-2680
    • Drullman, R.1    Festen, J.M.2    Plomp, R.3
  • 22
    • 21444432826 scopus 로고    scopus 로고
    • On the robustness of static and dynamic spectral information for speech recognition in noise,
    • Ph.D. dissertation, Chinese Univ. Hong Kong, Hong Kong
    • C. C. Yang, "On the robustness of static and dynamic spectral information for speech recognition in noise," Ph.D. dissertation, Chinese Univ. Hong Kong, Hong Kong, 2004.
    • (2004)
    • Yang, C.C.1
  • 23
    • 33646768933 scopus 로고    scopus 로고
    • Static and dynamic spectral features: Their noise robustness and optimal weights for asr
    • C. Yang, F. K. Soong, and T. Lee, "Static and dynamic spectral features: their noise robustness and optimal weights for asr," in Proc. ICASSP, 2005, pp. 241-244.
    • (2005) Proc. ICASSP , pp. 241-244
    • Yang, C.1    Soong, F.K.2    Lee, T.3
  • 24
    • 0036497677 scopus 로고    scopus 로고
    • Spoken language resources for Cantonese speech processing
    • T. Lee, W. K. Lo, P. C. Ching, and H. Meng, "Spoken language resources for Cantonese speech processing," Speech Commun., vol. 36, pp. 327-342, 2002.
    • (2002) Speech Commun , vol.36 , pp. 327-342
    • Lee, T.1    Lo, W.K.2    Ching, P.C.3    Meng, H.4
  • 26
    • 21444439750 scopus 로고    scopus 로고
    • Noise robustness of dynamic and static features for continuous Cantonese digit recognition
    • C. Yang, F. K. Soong, and T. Lee, "Noise robustness of dynamic and static features for continuous Cantonese digit recognition," in Proc. ISCSLP, 2004, pp. 277-280.
    • (2004) Proc. ISCSLP , pp. 277-280
    • Yang, C.1    Soong, F.K.2    Lee, T.3
  • 27
    • 85009151521 scopus 로고    scopus 로고
    • Explicit duration modeling for Cantonese connected- digit recognition
    • Y. Zhu and T. Lee, "Explicit duration modeling for Cantonese connected- digit recognition," in Proc. ICSLP, 2004, pp. 685-688.
    • (2004) Proc. ICSLP , pp. 685-688
    • Zhu, Y.1    Lee, T.2
  • 28
    • 0031619371 scopus 로고    scopus 로고
    • Balancing acoustic and linguistic probabilities
    • A. Ogawa, K. Takeda, and F. Itakura, "Balancing acoustic and linguistic probabilities," in Proc. ICASSP, 1998, pp. 181-184.
    • (1998) Proc. ICASSP , pp. 181-184
    • Ogawa, A.1    Takeda, K.2    Itakura, F.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.