메뉴 건너뛰기




Volumn , Issue , 1997, Pages KN33-KN36

Statistical Techniques for Robust ASR: Review and Perspectives

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH RECOGNITION;

EID: 84885532506     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (22)

References (33)
  • 1
    • 0026189808 scopus 로고
    • Speech Recognition in Adverse Environments
    • B.H. Jnang, "Speech Recognition in Adverse Environments," Comput. Speech Language, Vol. 5, pp. 275-294, 1991.
    • (1991) Comput. Speech Language , vol.5 , pp. 275-294
    • Jnang, B.H.1
  • 3
    • 0029288202 scopus 로고
    • Speech Recognition in Noisy Environments: A Survey
    • Y. Gong, "Speech Recognition in Noisy Environments: A Survey," Speech Comm., Vol. 16, pp. 261-291, 1995.
    • (1995) Speech Comm , vol.16 , pp. 261-291
    • Gong, Y.1
  • 5
    • 0002127129 scopus 로고
    • Probabilistic Optimum Filtering for Robust. Speech Recognition
    • L. Neumeyer and M. Weintraub, "Probabilistic Optimum Filtering for Robust. Speech Recognition," in Proc. ICASSP, Vol. I, pp. 417-420, 1994.
    • (1994) Proc. ICASSP , vol.I , pp. 417-420
    • Neumeyer, L.1    Weintraub, M.2
  • 6
    • 84919174492 scopus 로고
    • Statistical Signal Mapping: A General Tool for Speech Signal Processing
    • Y.M. Cheng, et al, "Statistical Signal Mapping: A General Tool for Speech Signal Processing," in Proc. 6th IEEE Worksh,. Stat. Sig., Array Proc, pp. 436-439, 1992.
    • (1992) Proc. 6th IEEE Worksh,. Stat. Sig., Array Proc , pp. 436-439
    • Cheng, Y.M.1
  • 7
    • 0027189327 scopus 로고
    • Speech Discrimination in Adverse Conditions Using Acoustic Knowledge and Selectively Trained Neural Networks
    • Y. Anglade, et al, "Speech Discrimination in Adverse Conditions Using Acoustic Knowledge and Selectively Trained Neural Networks," in Proc. ICASSP, Vol. II, pp. 279-282, 1993.
    • (1993) Proc. ICASSP , vol.II , pp. 279-282
    • Anglade, Y.1
  • 8
    • 34248650893 scopus 로고
    • A Hierarchical LPNN Network for Noise Reduction and Noise Degraded Speech Recognition
    • Y. Gao and J-P. Haton, "A Hierarchical LPNN Network for Noise Reduction and Noise Degraded Speech Recognition," in Proc. ICASSP, Vol. II, pp. 89-92, 1994.
    • (1994) Proc. ICASSP , vol.II , pp. 89-92
    • Gao, Y.1    Haton, J-P.2
  • 9
    • 0028420014 scopus 로고
    • Integrated Models of Signal and Background with Application To Speaker Identification in Noise
    • R.C. Rose, et al, "Integrated Models of Signal and Background with Application To Speaker Identification in Noise," IEEE Trans. SAP, Vol. 2, No. 2, pp. 245-257, 1994.
    • (1994) IEEE Trans. SAP , vol.2 , Issue.2 , pp. 245-257
    • Rose, R.C.1
  • 10
    • 0024753593 scopus 로고
    • Speech Recognition Using Noise-Adaptive Prototypes
    • A. Nadas, et al, "Speech Recognition Using Noise-Adaptive Prototypes," IEEE Trans. ASSP, Vol. 37, No. 10, pp. 1495-1502, 1989.
    • (1989) IEEE Trans. ASSP , vol.37 , Issue.10 , pp. 1495-1502
    • Nadas, A.1
  • 12
    • 0029726509 scopus 로고    scopus 로고
    • Improving Environmental Robustness in Large Vocabulary Speech Recognition
    • P.C. Woodland, et al, "Improving Environmental Robustness in Large Vocabulary Speech Recognition," in Proc. ICASSP, Vol. I, pp. 65-68, 1996.
    • (1996) Proc. ICASSP , vol.I , pp. 65-68
    • Woodland, P.C.1
  • 13
    • 0029769867 scopus 로고    scopus 로고
    • Signal Bias Removal by Maximum Likelihood Estimation for Robust Telephone Speech Recognition
    • M.G. Rahim and B.H. Juang, "Signal Bias Removal by Maximum Likelihood Estimation for Robust Telephone Speech Recognition," IEEE Trans. SAP, Vol. 4, No. 1, pp. 19-30, 1996.
    • (1996) IEEE Trans. SAP , vol.4 , Issue.1 , pp. 19-30
    • Rahim, M.G.1    Juang, B.H.2
  • 14
    • 44449087450 scopus 로고
    • Signal Processing for Robust Speech Recognition
    • et ai, in
    • F. Liu, et ai, "Signal Processing for Robust Speech Recognition," in Proc. ARPA Worksh. Human Lang. Tech., pp. 309-314, 1994.
    • (1994) Proc. ARPA Worksh. Human Lang. Tech , pp. 309-314
    • Liu, F.1
  • 15
    • 0028460810 scopus 로고
    • An Acoustic-Phonetic-Based Speaker Adaptation Technique Improving Speaker-Independent Continuous Speech Recognition
    • Y. Zhao, "An Acoustic-Phonetic-Based Speaker Adaptation Technique Improving Speaker-Independent Continuous Speech Recognition," IEEE Trans. SAP, Vol. 2, No. 3, pp. 380-394, 1994.
    • (1994) IEEE Trans. SAP , vol.2 , Issue.3 , pp. 380-394
    • Zhao, Y.1
  • 16
    • 0028997002 scopus 로고
    • Speaker Adaptation Based on Transfer Vector Field Smoothing Using MAP Estimation
    • M. Tonomura, et al, "Speaker Adaptation Based on Transfer Vector Field Smoothing Using MAP Estimation," in Proc. ICASSP, pp. 688-691, 1995.
    • (1995) Proc. ICASSP , pp. 688-691
    • Tonomura, M.1
  • 17
    • 0028419019 scopus 로고
    • Maximum A Posteriori Estimation for Multivariate Gaussian Mixture Observations of Markov Chains
    • J.L. Gauvain and C.H. Lee, "Maximum A Posteriori Estimation for Multivariate Gaussian Mixture Observations of Markov Chains," IEEE Trans. SAP, Vol. 2, No. 2, pp. 291-298, 1994.
    • (1994) IEEE Trans. SAP , vol.2 , Issue.2 , pp. 291-298
    • Gauvain, J.L.1    Lee, C.H.2
  • 19
    • 0030149866 scopus 로고    scopus 로고
    • A Maximum-Likelihood Approach to Stochastic Matching for Robust Speech Recognition
    • A. Sankar and C.H. Lee, "A Maximum-Likelihood Approach to Stochastic Matching for Robust Speech Recognition," IEEE Trans. SAP, Vol. 4, No. 2, pp. 190-202, 1996.
    • (1996) IEEE Trans. SAP , vol.4 , Issue.2 , pp. 190-202
    • Sankar, A.1    Lee, C.H.2
  • 20
    • 0028996861 scopus 로고
    • Multivariate-Gaussian-Based Cepstral Normalization for Robust Speech Recognition
    • et ai, in
    • P.J. Moreno, et ai, "Multivariate-Gaussian-Based Cepstral Normalization for Robust Speech Recognition," in Proc. ICASSP, pp. 137-140, 1995.
    • (1995) Proc. ICASSP , pp. 137-140
    • Moreno, P.J.1
  • 21
    • 85079234583 scopus 로고
    • On the Limitations of Cepstral Features in Noise
    • and 7
    • J.P. Openshaw and .7.S. Mason, "On the Limitations of Cepstral Features in Noise," in Proc. ICASSP, Vol. II, pp. 49-52, 1994.
    • (1994) Proc. ICASSP , vol.II , pp. 49-52
    • Openshaw, J.P.1    Mason, S.2
  • 22
    • 0029288633 scopus 로고
    • Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density Hidden Markov Models
    • C.J. Leggetter and P.C. Woodland, "Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density Hidden Markov Models," Comput. Speech. Lanquaqe, Vol. 9, No. 2. pp. 171-186, 1995.
    • (1995) Comput. Speech. Lanquaqe , vol.9 , Issue.2 , pp. 171-186
    • Leggetter, C.J.1    Woodland, P.C.2
  • 23
    • 0030263447 scopus 로고    scopus 로고
    • Mean and Variance Adaptation Within the MLLR Framework
    • M.J.F. Gales and P.C. Woodland, "Mean and Variance Adaptation Within the MLLR Framework," Comput. Speech. Lemquaqe, Vol. 10, pp. 249-264, 1996.
    • (1996) Comput. Speech. Lemquaqe , vol.10 , pp. 249-264
    • Gales, M.J.F.1    Woodland, P.C.2
  • 24
    • 0030362995 scopus 로고    scopus 로고
    • A Compact Model for Speaker-Adaptive Training
    • et ai, in
    • T. Anastasakos, et ai, "A Compact Model for Speaker-Adaptive Training," in Proc 4th K'SLP, pp. 1137-1140, 1996.
    • (1996) Proc 4th K'SLP , pp. 1137-1140
    • Anastasakos, T.1
  • 25
    • 0028463296 scopus 로고
    • The Metamorplnc Algorithm: A Speaker Mapping Approach to Data Augmentation
    • J.R. Bellegarda, et al, "The Metamorplnc Algorithm: A Speaker Mapping Approach to Data Augmentation," IEEE Trans. SAP, Vol. 2, No. 3, pp. 413-420, 1994.
    • (1994) IEEE Trans. SAP , vol.2 , Issue.3 , pp. 413-420
    • Bellegarda, J.R.1
  • 26
    • 84937854847 scopus 로고
    • Speaker-Adaptation for Hybrid HMM-ANN Continuous Speech Recognition System
    • J. Neto, et al, "Speaker-Adaptation for Hybrid HMM-ANN Continuous Speech Recognition System," in Proc. EuroSpeech'95, pp. 2171-2174. 1995.
    • (1995) Proc. EuroSpeech'95 , pp. 2171-2174
    • Neto, J.1
  • 27
    • 85009095555 scopus 로고    scopus 로고
    • A Vector Taylor Series Approach for Environment-Independent Speech Recognition
    • P.J. Moreno, et al, "A Vector Taylor Series Approach for Environment-Independent Speech Recognition," in Proc. ICASSP, pp. 835-838, 1997.
    • (1997) Proc. ICASSP , pp. 835-838
    • Moreno, P.J.1
  • 28
    • 0030649027 scopus 로고    scopus 로고
    • Jacobian Approach To Fast Acoustic Model Adaptation
    • S. Sagayama, et al, "Jacobian Approach To Fast Acoustic Model Adaptation," in Proc ICASSP, pp. 835-838, 1997.
    • (1997) Proc ICASSP , pp. 835-838
    • Sagayama, S.1
  • 29
    • 0030674098 scopus 로고    scopus 로고
    • A Unified Maximum Likelihood Approach to Acoustic Mismatch Compensation: Application to Noisy Lombard Speech Recognition
    • M. Afify, et al, "A Unified Maximum Likelihood Approach to Acoustic Mismatch Compensation: Application to Noisy Lombard Speech Recognition," in Proc. ICASSP, pp. 839-842, 1997.
    • (1997) Proc. ICASSP , pp. 839-842
    • Afify, M.1
  • 30
    • 0030643678 scopus 로고    scopus 로고
    • Improved Bayesian Learning of Hidden Markov Models for Speaker Adaptation
    • J.T. Chien, et al, "Improved Bayesian Learning of Hidden Markov Models for Speaker Adaptation," in Proc. ICASSP, pp. 1027-1030, 1997.
    • (1997) Proc. ICASSP , pp. 1027-1030
    • Chien, J.T.1
  • 31
    • 0030189744 scopus 로고    scopus 로고
    • Speaker Adaptation Using Combined Transformation and Bayesian Methods
    • V. Digalakis and L. Neumeyer, "Speaker Adaptation Using Combined Transformation and Bayesian Methods," IEEE Trans. SAP, Vol. 4, No. 3, pp. 294-300, 1996.
    • (1996) IEEE Trans. SAP , vol.4 , Issue.3 , pp. 294-300
    • Digalakis, V.1    Neumeyer, L.2
  • 32
    • 0029745232 scopus 로고    scopus 로고
    • Maximum A Posteriori for Large Scale HMM Recognizers
    • G. Zavaliagkos, et al, "Maximum A Posteriori for Large Scale HMM Recognizers," in Proc ICASSP. Vol. I, pp. 725-728, 1996.
    • (1996) Proc ICASSP , vol.I , pp. 725-728
    • Zavaliagkos, G.1
  • 33
    • 0029747193 scopus 로고    scopus 로고
    • Speaker Adaptation with Autonomous Model Complexity Control by MDL Principle
    • K. Shinoda and T. Watanabe, "Speaker Adaptation with Autonomous Model Complexity Control by MDL Principle," in Proc ICASSP, pp.' 717-720, 1996.
    • (1996) Proc ICASSP , pp. 717-720
    • Shinoda, K.1    Watanabe, T.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.