메뉴 건너뛰기




Volumn 15, Issue 5, 2007, Pages 1724-1730

Noise-robust automatic speech recognition using a predictive echo state network

Author keywords

Digit recognition; Noise robust automatic speech recognition; Predictive echo state network

Indexed keywords

HIDDEN MARKOV MODELS; RECURRENT NEURAL NETWORKS; SIGNAL TO NOISE RATIO;

EID: 34548827187     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2007.896669     Document Type: Article
Times cited : (68)

References (43)
  • 1
    • 0025682327 scopus 로고
    • Word recognition using hidden control neural architecture
    • Albuquerque, NM, Apr
    • E. Levin, "Word recognition using hidden control neural architecture," in Proc. Int. Conf. Acoust., Speech, Signal Process., Albuquerque, NM, Apr. 1990, vol. 1, pp. 433-436.
    • (1990) Proc. Int. Conf. Acoust., Speech, Signal Process , vol.1 , pp. 433-436
    • Levin, E.1
  • 2
    • 0026406315 scopus 로고
    • Large vocabulary speech recognition using neural prediction model
    • Toronto, ON, Canada, May
    • K. Iso and T. Watanabe, "Large vocabulary speech recognition using neural prediction model," in Proc. Int. Conf. Acoust., Speech, Signal Process., Toronto, ON, Canada, May 1991, vol. 1, pp. 57-60.
    • (1991) Proc. Int. Conf. Acoust., Speech, Signal Process , vol.1 , pp. 57-60
    • Iso, K.1    Watanabe, T.2
  • 3
    • 0025642110 scopus 로고
    • Large vocabulary recognition using linked predictive neural networks
    • Albuquerque, NM, Apr
    • J. Tebelskis and A. Waibel, "Large vocabulary recognition using linked predictive neural networks," in Proc. Int. Conf. Acoust., Speech, and Signal Process., Albuquerque, NM, Apr. 1990, vol. 1, pp. 437-440.
    • (1990) Proc. Int. Conf. Acoust., Speech, and Signal Process , vol.1 , pp. 437-440
    • Tebelskis, J.1    Waibel, A.2
  • 4
    • 0004080016 scopus 로고
    • Speech recognition using neural networks,
    • Ph.D. dissertation, Carnegie Mellon Univerity, Pittsburgh, PA
    • J. Tebelskis, "Speech recognition using neural networks," Ph.D. dissertation, Carnegie Mellon Univerity, Pittsburgh, PA, 1995.
    • (1995)
    • Tebelskis, J.1
  • 5
    • 0033709733 scopus 로고    scopus 로고
    • On the predictive connectionist models for automatic speech recognition
    • Istanbul, Turkey, Jun
    • B. Petek, "On the predictive connectionist models for automatic speech recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process., Istanbul, Turkey, Jun. 2000, vol. 1, pp. 3442-3445.
    • (2000) Proc. Int. Conf. Acoust., Speech, Signal Process , vol.1 , pp. 3442-3445
    • Petek, B.1
  • 7
    • 0029308753 scopus 로고
    • Neural networks for statistical recognition of continuous speech
    • May
    • N. Morgan and H. A. Bourlard, "Neural networks for statistical recognition of continuous speech," Proc. IEEE, vol. 83, no. 5, pp. 742-772, May 1995.
    • (1995) Proc. IEEE , vol.83 , Issue.5 , pp. 742-772
    • Morgan, N.1    Bourlard, H.A.2
  • 8
    • 0025671510 scopus 로고
    • A probabilistic approach to the understanding and training of neural network classifiers
    • Albuquerque, NM, Apr
    • H. Gish, "A probabilistic approach to the understanding and training of neural network classifiers," in Proc. Int. Conf. Acoust., Speech, Signal Process., Albuquerque, NM, Apr. 1990, vol. 1, pp. 1361-1364.
    • (1990) Proc. Int. Conf. Acoust., Speech, Signal Process , vol.1 , pp. 1361-1364
    • Gish, H.1
  • 9
    • 0028392167 scopus 로고
    • An application of recurrent nets to phone probability estimation
    • Mar
    • A. J. Robinson, "An application of recurrent nets to phone probability estimation," IEEE Trans. Neural Netw., vol. 5, no. 2, pp. 298-305, Mar. 1994.
    • (1994) IEEE Trans. Neural Netw , vol.5 , Issue.2 , pp. 298-305
    • Robinson, A.J.1
  • 10
    • 0025594074 scopus 로고
    • Connectionist Viterbi training: A new hybrid method for continuous speech recognition
    • Albuquerque, NM, Apr
    • M. Franzini, K.-F. Lee, and A.Waibel, "Connectionist Viterbi training: A new hybrid method for continuous speech recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process., Albuquerque, NM, Apr. 1990, vol. 1, pp. 425-428.
    • (1990) Proc. Int. Conf. Acoust., Speech, Signal Process , vol.1 , pp. 425-428
    • Franzini, M.1    Lee, K.-F.2    Waibel, A.3
  • 11
    • 27744588611 scopus 로고    scopus 로고
    • Framewise phoneme classification with bidirectional LSTM and other neural network architectures
    • Jun.-Jul
    • A. Graves and J. Schmidhuber, "Framewise phoneme classification with bidirectional LSTM and other neural network architectures," Neural Netw., vol. 18, no. 5-6, pp. 602-610, Jun.-Jul. 2005.
    • (2005) Neural Netw , vol.18 , Issue.5-6 , pp. 602-610
    • Graves, A.1    Schmidhuber, J.2
  • 12
    • 0742286348 scopus 로고    scopus 로고
    • Robust combination of neural networks and hidden Markov models for speech recognition
    • Nov
    • E. Trentin and M. Gori, "Robust combination of neural networks and hidden Markov models for speech recognition," Neural Netw., vol. 14, no. 6, pp. 1519-1531, Nov. 2003.
    • (2003) Neural Netw , vol.14 , Issue.6 , pp. 1519-1531
    • Trentin, E.1    Gori, M.2
  • 13
    • 0035340181 scopus 로고    scopus 로고
    • A continuous density interpretation of discrete hmm systems and mmi-neural networks
    • May
    • C. Neukirchen, J. Rottland, D. Willett, and G. Rigoll, "A continuous density interpretation of discrete hmm systems and mmi-neural networks," IEEE Trans. Speech Audio Process., vol. 9, no. 4, pp. 367-377, May 2001.
    • (2001) IEEE Trans. Speech Audio Process , vol.9 , Issue.4 , pp. 367-377
    • Neukirchen, C.1    Rottland, J.2    Willett, D.3    Rigoll, G.4
  • 14
    • 0000800741 scopus 로고
    • A tutorial on hidden Markov models and selected applications in speech recognition
    • A. Waibel and K.-F Lee, Eds. San Mateo, CA: Kaufmann
    • L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," in Readings in Speech Recognition, A. Waibel and K.-F Lee, Eds. San Mateo, CA: Kaufmann, 1990, pp. 267-296.
    • (1990) Readings in Speech Recognition , pp. 267-296
    • Rabiner, L.R.1
  • 16
    • 0038669544 scopus 로고    scopus 로고
    • The Aurora experimental framework for the performance evaluation of speech recognition systems under noise conditions
    • Paris, France
    • H. G. Hirsch and D. Pearce, "The Aurora experimental framework for the performance evaluation of speech recognition systems under noise conditions," in Proc. Int. Speech Commun. Assoc. Tutorial Res. Workshop ASR2000, Paris, France, 2000, pp. 181-188.
    • (2000) Proc. Int. Speech Commun. Assoc. Tutorial Res. Workshop ASR2000 , pp. 181-188
    • Hirsch, H.G.1    Pearce, D.2
  • 17
    • 64149114412 scopus 로고    scopus 로고
    • D. E. Rumelhart, G. E. Hinton, and R. J. Williams, Learning internal representations by error propagation, in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, D. E. Rumelhart and J. L. McClelland, Eds. Cambridge, MA: MIT Press, 1986, 1, Foundations, pp. 318-362.
    • D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representations by error propagation," in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, D. E. Rumelhart and J. L. McClelland, Eds. Cambridge, MA: MIT Press, 1986, vol. 1, Foundations, pp. 318-362.
  • 19
    • 0023936027 scopus 로고
    • Learning the hidden structure of speech
    • Apr
    • J. L. Elman and D. Zipser, "Learning the hidden structure of speech," J. Acoust. Soc. Amer., vol. 83, no. 4, pp. 1615-1626, Apr. 1988.
    • (1988) J. Acoust. Soc. Amer , vol.83 , Issue.4 , pp. 1615-1626
    • Elman, J.L.1    Zipser, D.2
  • 20
    • 0034186923 scopus 로고    scopus 로고
    • New results on recurrent network training: Unifying the algorithms and accelerating convergence
    • May
    • A. F. Atiya and A. G. Parlos, "New results on recurrent network training: Unifying the algorithms and accelerating convergence," IEEE Trans. Neural Netw., vol. 11, no. 3, pp. 697-709, May 2000.
    • (2000) IEEE Trans. Neural Netw , vol.11 , Issue.3 , pp. 697-709
    • Atiya, A.F.1    Parlos, A.G.2
  • 21
    • 64149084089 scopus 로고    scopus 로고
    • H. Jaeger, The echo state approach to analysing and training recurrent neural networks, German National Res. Center Inf. Technol., Fraunhofer Inst. Auton. Intell. Syst., GMD Rep. 148, Dec. 2001, Tech. Rep.
    • H. Jaeger, "The "echo state" approach to analysing and training recurrent neural networks," German National Res. Center Inf. Technol., Fraunhofer Inst. Auton. Intell. Syst., GMD Rep. 148, Dec. 2001, Tech. Rep.
  • 22
    • 0003807773 scopus 로고    scopus 로고
    • 4th ed. Upper Saddle River, NJ: Prentice-Hall
    • S. Haykin, Adaptive Filter Theory, 4th ed. Upper Saddle River, NJ: Prentice-Hall, 2001.
    • (2001) Adaptive Filter Theory
    • Haykin, S.1
  • 23
    • 78349289898 scopus 로고    scopus 로고
    • Adaptive nonlinear system identification with echo state networks
    • S. T. S. Becker and K. Obermayer, Eds. Cambridge, MA:MIT Press
    • H. Jaeger, "Adaptive nonlinear system identification with echo state networks," in Advances in Neural Information Processing Systems, 2002, S. T. S. Becker and K. Obermayer, Eds. Cambridge, MA:MIT Press, 2003, pp. 593-600.
    • (2003) Advances in Neural Information Processing Systems, 2002 , pp. 593-600
    • Jaeger, H.1
  • 24
    • 1842421269 scopus 로고    scopus 로고
    • Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication
    • H. Jaeger and H. Haas, "Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication," Science, vol. 304, no. 5667, pp. 78-80, 2004.
    • (2004) Science , vol.304 , Issue.5667 , pp. 78-80
    • Jaeger, H.1    Haas, H.2
  • 25
    • 34249867443 scopus 로고    scopus 로고
    • Automatic speech recognition using a predictive echo state network classifier
    • to be published
    • M. D. Skowronski and J. G. Harris, "Automatic speech recognition using a predictive echo state network classifier," Neural Netw., 2007, to be published.
    • (2007) Neural Netw
    • Skowronski, M.D.1    Harris, J.G.2
  • 27
    • 26844524748 scopus 로고    scopus 로고
    • Signal processing in a nonlinear, non-Gaussian and nonstationary world
    • G. Chollet, A. Esposito, M. Faundez-Zanuy, and M. Marinaro, Eds. Berlin: Springer-Verlag
    • S. Haykin, "Signal processing in a nonlinear, non-Gaussian and nonstationary world," in Nonlinear Speech Modeling and Applications, G. Chollet, A. Esposito, M. Faundez-Zanuy, and M. Marinaro, Eds. Berlin: Springer-Verlag, 2005, pp. 43-53.
    • (2005) Nonlinear Speech Modeling and Applications , pp. 43-53
    • Haykin, S.1
  • 28
    • 0025493667 scopus 로고
    • The segmental K-means algorithm for estimating parameters of hidden Markov models
    • Sep
    • B.-H. Juang and L. R. Rabiner, "The segmental K-means algorithm for estimating parameters of hidden Markov models," IEEE Trans. Acoust., Speech, Signal Process., vol. 38, no. 9, pp. 1639-1641, Sep. 1990.
    • (1990) IEEE Trans. Acoust., Speech, Signal Process , vol.38 , Issue.9 , pp. 1639-1641
    • Juang, B.-H.1    Rabiner, L.R.2
  • 29
    • 0001940458 scopus 로고
    • Adaptive mixtures of local experts
    • Spring
    • R. A. Jacobs, M. I. Jordan, S. J. Nowlan, and G. E. Hinton, "Adaptive mixtures of local experts," Neural Comput., vol. 3, no. 1, pp. 79-87, Spring, 1991.
    • (1991) Neural Comput , vol.3 , Issue.1 , pp. 79-87
    • Jacobs, R.A.1    Jordan, M.I.2    Nowlan, S.J.3    Hinton, G.E.4
  • 30
    • 64149091204 scopus 로고    scopus 로고
    • S. Young, J. Jansen, J. Odell, D. Ollasen, and P. Woodland, The HTK Book Version 2.0, Cambridge, U.K, Entropics Cambridge Research Lab, 1995
    • S. Young, J. Jansen, J. Odell, D. Ollasen, and P. Woodland, The HTK Book (Version 2.0). Cambridge, U.K.: Entropics Cambridge Research Lab, 1995.
  • 31
    • 4444368779 scopus 로고    scopus 로고
    • Exploiting independent filter bandwidth of human factor cepstral coefficients in automatic speech recognition
    • Sep
    • M. D. Skowronski and J. G. Harris, "Exploiting independent filter bandwidth of human factor cepstral coefficients in automatic speech recognition," J. Acoust. Soc. Amer., vol. 116, no. 3, pp. 1774-1780, Sep. 2004.
    • (2004) J. Acoust. Soc. Amer , vol.116 , Issue.3 , pp. 1774-1780
    • Skowronski, M.D.1    Harris, J.G.2
  • 32
    • 0019555090 scopus 로고
    • Cepstral analysis technique for automatic speaker verification
    • Apr
    • S. Furui, "Cepstral analysis technique for automatic speaker verification," IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-29, no. 2, pp. 254-272, Apr. 1981.
    • (1981) IEEE Trans. Acoust., Speech, Signal Process , vol.ASSP-29 , Issue.2 , pp. 254-272
    • Furui, S.1
  • 33
    • 0016067897 scopus 로고
    • Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification
    • Jun
    • B. S. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. Amer., vol. 55, no. 6, pp. 1304-1312, Jun. 1974.
    • (1974) J. Acoust. Soc. Amer , vol.55 , Issue.6 , pp. 1304-1312
    • Atal, B.S.1
  • 35
    • 33750099080 scopus 로고    scopus 로고
    • Reservoir riddles: Suggestions for echo state network research
    • Montreal, QC, Canada, Jul
    • H. Jaeger, "Reservoir riddles: Suggestions for echo state network research," in Proc. Int. Joint Conf. Neural Netw.,Montreal, QC, Canada, Jul. 2005, pp. 1460-1462.
    • (2005) Proc. Int. Joint Conf. Neural Netw , pp. 1460-1462
    • Jaeger, H.1
  • 36
    • 33750112286 scopus 로고    scopus 로고
    • Echo state networks: Appeal and challenges
    • Montreal, QC, Canada, Jul
    • D. Prokhorov, "Echo state networks: Appeal and challenges," in Proc. Int. Joint Conf. Neural Netw., Montreal, QC, Canada, Jul. 2005, pp. 1463-1466.
    • (2005) Proc. Int. Joint Conf. Neural Netw , pp. 1463-1466
    • Prokhorov, D.1
  • 37
    • 84918441630 scopus 로고
    • Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition
    • Jun
    • T. M. Cover, "Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition," IEEE Trans. Electron. Comput., vol. EC-14, no. 3, pp. 326-334, Jun. 1965.
    • (1965) IEEE Trans. Electron. Comput , vol.EC-14 , Issue.3 , pp. 326-334
    • Cover, T.M.1
  • 39
    • 0029345417 scopus 로고
    • A signal subspace approach for speech enhancement
    • Jul
    • Y. Ephraim and H. L. 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.L.2
  • 40
    • 0031238095 scopus 로고    scopus 로고
    • A model of dynamic auditory perception and its application to robust word recognition
    • Sep
    • B. Strope and A. Alwan, "A model of dynamic auditory perception and its application to robust word recognition," IEEE Trans. Speech Audio Process., vol. 5, no. 5, pp. 451-464, Sep. 1997.
    • (1997) IEEE Trans. Speech Audio Process , vol.5 , Issue.5 , pp. 451-464
    • Strope, B.1    Alwan, A.2
  • 41
    • 0029288202 scopus 로고
    • Speech recognition in noisy environments: A survey
    • Y. Gong, "Speech recognition in noisy environments: A survey," Speech Commun., vol. 16, pp. 261-291, 1995.
    • (1995) Speech Commun , vol.16 , pp. 261-291
    • Gong, Y.1
  • 42
    • 18744401086 scopus 로고    scopus 로고
    • Dynamic compensation of hmm variances using the feature enhancement uncertainty computed from a parametric model of speech distortion
    • May
    • L. Deng, J. Droppo, and A. Acero, "Dynamic compensation of hmm variances using the feature enhancement uncertainty computed from a parametric model of speech distortion," IEEE Trans. Speech Audio Process., vol. 13, no. 3, pp. 412-421, May 2005.
    • (2005) IEEE Trans. Speech Audio Process , vol.13 , Issue.3 , pp. 412-421
    • Deng, L.1    Droppo, J.2    Acero, A.3
  • 43
    • 34548824389 scopus 로고    scopus 로고
    • Noise-robust automatic speech recognition using a discriminative echo state network
    • New Orleans, LA, to be published
    • M. D. Skowronski and J. G. Harris, "Noise-robust automatic speech recognition using a discriminative echo state network," in Proc. Int. Symp. Circuits Syst., New Orleans, LA, 2007, to be published.
    • (2007) Proc. Int. Symp. Circuits Syst
    • Skowronski, M.D.1    Harris, J.G.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.