메뉴 건너뛰기




Volumn 4, Issue 3, 2010, Pages 540-547

Gaussian mixture optimization based on efficient cross-validation

Author keywords

Cross validation; Gaussian mixture; Hidden Markov model (HMM); Speech recognition; Sufficient statistics

Indexed keywords

COMPUTATIONAL COSTS; CROSS VALIDATION; EVALUATION ALGORITHM; GAUSSIAN MIXTURE; GAUSSIAN MIXTURES; GAUSSIANS; GENERALIZATION PERFORMANCE; MIXTURE COMPONENTS; MODEL COMPLEXITY; OBJECTIVE FUNCTIONS; OPTIMIZATION METHOD; ORAL PRESENTATIONS; OVERFITTING; RECOGNITION PERFORMANCE; SPEECH RECOGNITION PERFORMANCE; STEP-BY-STEP; SUFFICIENT STATISTICS; TERMINATION CRITERIA; TRAINING SETS;

EID: 77952624645     PISSN: 19324553     EISSN: None     Source Type: Journal    
DOI: 10.1109/JSTSP.2010.2048235     Document Type: Article
Times cited : (7)

References (30)
  • 2
    • 10044240378 scopus 로고    scopus 로고
    • Improved adaptive gaussian mixture model for background subtraction
    • Z. Zivkovic, "Improved adaptive gaussian mixture model for background subtraction, " in Proc. ICPR, 2004, vol. 2, pp. 23-26.
    • (2004) Proc. ICPR , vol.2 , pp. 23-26
    • Zivkovic, Z.1
  • 3
    • 34547504101 scopus 로고    scopus 로고
    • Model complexity selection and cross-validation EM training for robust speaker diarization
    • X. Anguera, T. Shinozaki, C. Wooters, and J. Hernando, "Model complexity selection and cross-validation EM training for robust speaker diarization, " in Proc. ICASSP, 2007, vol. IV, pp. 273-276.
    • (2007) Proc. ICASSP , vol.4 , pp. 273-276
    • Anguera, X.1    Shinozaki, T.2    Wooters, C.3    Hernando, J.4
  • 5
    • 0016355478 scopus 로고
    • A new look at the statistical model identification
    • Dec
    • H. Akaike, "A new look at the statistical model identification, " IEEE Trans. Autom. Control, vol. AC-19, no. 6, pp. 716-723, Dec. 1974.
    • (1974) IEEE Trans. Autom. Control , vol.AC-19 , Issue.6 , pp. 716-723
    • Akaike, H.1
  • 6
    • 0021466584 scopus 로고
    • Universal coding, information, prediction, and estimation
    • Jul
    • J. Rissanen, "Universal coding, information, prediction, and estimation, " IEEE Trans. Inf. Theory, vol. IT-30, no. 4, pp. 629-638, Jul. 1984.
    • (1984) IEEE Trans. Inf. Theory , vol.IT-30 , Issue.4 , pp. 629-638
    • Rissanen, J.1
  • 7
    • 85135145174 scopus 로고    scopus 로고
    • Acoustic modeling based on the MDL principle for speech recognition
    • K. Shinoda and T. Watanabe, "Acoustic modeling based on the MDL principle for speech recognition, " in Proc. Eurospeech, 1997, vol. 1, pp. 99-102.
    • (1997) Proc. Eurospeech , vol.1 , pp. 99-102
    • Shinoda, K.1    Watanabe, T.2
  • 8
    • 34147153716 scopus 로고    scopus 로고
    • A comparative evaluation of variance flooring techniques in HMM-based speaker verification
    • in, Sydney, Australia
    • H. Melin, J. W. Koolwaaij, J. Lindberg, and F. Bimbot, "A comparative evaluation of variance flooring techniques in HMM-based speaker verification, " in Proc. ICSLP, Sydney, Australia, 1998, pp. 2379-2382.
    • (1998) Proc. ICSLP , pp. 2379-2382
    • Melin, H.1    Koolwaaij, J.W.2    Lindberg, J.3    Bimbot, F.4
  • 11
    • 0017336301 scopus 로고
    • Asymptotics for and against cross-validation
    • Apr
    • M. Stone, "Asymptotics for and against cross-validation, " Biometrika, vol. 64, no. 1, pp. 29-35, Apr. 1977.
    • (1977) Biometrika , vol.64 , Issue.1 , pp. 29-35
    • Stone, M.1
  • 12
    • 85135141040 scopus 로고    scopus 로고
    • Automatic architecture design by likelihood-based context clustering with crossvalidation
    • in, Rhodes, Greece
    • I. Rogina, "Automatic architecture design by likelihood-based context clustering with crossvalidation, " in Proc. Eurospeech, Rhodes, Greece, 1997, pp. 1223-1226.
    • (1997) Proc. Eurospeech , pp. 1223-1226
    • Rogina, I.1
  • 13
    • 33947650089 scopus 로고    scopus 로고
    • HMM state clustering based on efficient cross-validation
    • in, Toulouse, France
    • T. Shinozaki, "HMM state clustering based on efficient cross-validation, " in Proc. ICASSP, Toulouse, France, 2006, vol. I, pp. 1157-1160.
    • (2006) Proc. ICASSP , vol.1 , pp. 1157-1160
    • Shinozaki, T.1
  • 14
    • 44849119309 scopus 로고    scopus 로고
    • Gaussian mixture optimization for HMM based on efficient cross-validation
    • T. Shinozaki and T. Kawahara, "Gaussian mixture optimization for HMM based on efficient cross-validation, " in Proc. Interspeech, 2007, pp. 2061-2064.
    • (2007) Proc. Interspeech , pp. 2061-2064
    • Shinozaki, T.1    Kawahara, T.2
  • 15
    • 0030715097 scopus 로고    scopus 로고
    • HMM topology design using maximum likelihood successive state splitting
    • M. Ostendorf and H. Singer, "HMM topology design using maximum likelihood successive state splitting, " Comput. Speech Lang., vol. 11, pp. 17-41, 1997.
    • (1997) Comput. Speech Lang. , vol.11 , pp. 17-41
    • Ostendorf, M.1    Singer, H.2
  • 16
    • 33645797655 scopus 로고    scopus 로고
    • Utterance-based selective training for the automatic creation of task-dependent acoustic models
    • T. Cincarek, T. Tomoki, H. Saruwatari, and K. Shikano, "Utterance-based selective training for the automatic creation of task-dependent acoustic models, " IEICE Trans. Inf. Syst., vol. E89-D, no. 3, pp. 962-969, 2006.
    • (2006) IEICE Trans. Inf. Syst. , vol.E89-D , Issue.3 , pp. 962-969
    • Cincarek, T.1    Tomoki, T.2    Saruwatari, H.3    Shikano, K.4
  • 17
    • 84867216283 scopus 로고    scopus 로고
    • Aggregated cross-validation and its efficient application to Gaussian mixture optimization
    • T. Shinozaki, S. Furui, and T. Kawahara, "Aggregated cross-validation and its efficient application to Gaussian mixture optimization, " in Proc. Interspeech, 2008, pp. 2382-2385.
    • (2008) Proc. Interspeech , pp. 2382-2385
    • Shinozaki, T.1    Furui, S.2    Kawahara, T.3
  • 18
    • 0030211964 scopus 로고    scopus 로고
    • Bagging predictors
    • L. Breiman, "Bagging predictors, " Mach. Learn., vol. 24, no. 2, pp. 123-140, 1996.
    • (1996) Mach. Learn. , vol.24 , Issue.2 , pp. 123-140
    • Breiman, L.1
  • 19
    • 35549000218 scopus 로고    scopus 로고
    • Cross-validation and aggregated EM training for robust parameter estimation
    • T. Shinozaki and M. Ostendorf, "Cross-validation and aggregated EM training for robust parameter estimation, " Comput. Speech Lang., vol. 22, no. 2, pp. 185-195, 2008.
    • (2008) Comput. Speech Lang. , vol.22 , Issue.2 , pp. 185-195
    • Shinozaki, T.1    Ostendorf, M.2
  • 20
    • 51449090592 scopus 로고    scopus 로고
    • GMM and HMM training by aggregatedEM algorithm with increased ensemble sizes for robust parameter estimation
    • T. Shinozaki and T. Kawahara, "GMM and HMM training by aggregatedEM algorithm with increased ensemble sizes for robust parameter estimation, " in Proc. ICASSP, 2008, pp. 4405-4408.
    • (2008) Proc. ICASSP , pp. 4405-4408
    • Shinozaki, T.1    Kawahara, T.2
  • 21
    • 0002629270 scopus 로고
    • Maximum likelihood from incomplete data via the EM algorithm
    • no. Series B 39
    • A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm, " J. R. Statist. Soc., no. 1, pp. 1-38, 1977, no. Series B 39.
    • (1977) J. R. Statist. Soc. , Issue.1 , pp. 1-38
    • Dempster, A.P.1    Laird, N.M.2    Rubin, D.B.3
  • 22
    • 3042854734 scopus 로고    scopus 로고
    • Benchmark test for speech recognition using the Corpus of Spontaneous Japanese
    • T. Kawahara, H. Nanjo, T. Shinozaki, and S. Furui, "Benchmark test for speech recognition using the Corpus of Spontaneous Japanese, " in Proc. SSPR2003, 2003, pp. 135-138.
    • (2003) Proc. SSPR2003 , pp. 135-138
    • Kawahara, T.1    Nanjo, H.2    Shinozaki, T.3    Furui, S.4
  • 23
    • 0003822743 scopus 로고    scopus 로고
    • Cambridge, U. K.: Cambridge Univ. Eng. Dept.
    • S. Young et al., The HTK Book. Cambridge, U. K.: Cambridge Univ. Eng. Dept., 2005.
    • (2005) The HTK Book
    • Young, S.1
  • 24
    • 85128340946 scopus 로고    scopus 로고
    • An efficient two-pass search algorithm using word trellis index
    • A. Lee, T. Kawahara, and S. Doshita, "An efficient two-pass search algorithm using word trellis index, " in Proc. ICSLP, 1998, pp. 1831-1834.
    • (1998) Proc. ICSLP , pp. 1831-1834
    • Lee, A.1    Kawahara, T.2    Doshita, S.3
  • 25
    • 0024909979 scopus 로고    scopus 로고
    • Some statistical issues in the comparison of speech recognition algorithms
    • L. Gillick and S. Cox, "Some statistical issues in the comparison of speech recognition algorithms, " in Proc. ICASSP, vol. 89, pp. 532-535.
    • Proc. ICASSP , vol.89 , pp. 532-535
    • Gillick, L.1    Cox, S.2
  • 26
    • 0033225865 scopus 로고    scopus 로고
    • An introduction to variational methods for graphical models
    • M. I. Jordan, Z. Ghahramani, T. S. Jaakkola, and L. K. Saul, "An introduction to variational methods for graphical models, " Mach. Learn., vol. 37, pp. 183-233, 1999.
    • (1999) Mach. Learn. , vol.37 , pp. 183-233
    • Jordan, M.I.1    Ghahramani, Z.2    Jaakkola, T.S.3    Saul, L.K.4
  • 27
    • 33646418145 scopus 로고    scopus 로고
    • Automatic determination of acoustic model topology using variational Bayesian estimation and clustering for large vocabulary continuous speech recognition
    • May
    • S. Watanabe, A. Sako, and A. Nakamura, "Automatic determination of acoustic model topology using variational Bayesian estimation and clustering for large vocabulary continuous speech recognition, " IEEE Trans. Speech Audio Process., vol. 14, no. 3, pp. 855-872, May 2006.
    • (2006) IEEE Trans. Speech Audio Process. , vol.14 , Issue.3 , pp. 855-872
    • Watanabe, S.1    Sako, A.2    Nakamura, A.3
  • 28
    • 84867213785 scopus 로고    scopus 로고
    • Bayesian context clustering using cross valid prior distribution for HMM-based speech recognition
    • K. Hashimoto, H. Zen, Y. Nankaku, A. Lee, and K. Tokuda, "Bayesian context clustering using cross valid prior distribution for HMM-based speech recognition, " in Proc. Interspeech, 2008, pp. 936-939.
    • (2008) Proc. Interspeech , pp. 936-939
    • Hashimoto, K.1    Zen, H.2    Nankaku, Y.3    Lee, A.4    Tokuda, K.5
  • 29
    • 0022890536 scopus 로고
    • Maximum mutual information estimation of hidden Markov model parameters for speech recognition
    • L. R. Bahl, P. F. Brown, P. V. de Souza, and R. L. Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition, " in Proc. ICASSP, 1986, pp. 49-52.
    • (1986) Proc. ICASSP , pp. 49-52
    • Bahl, L.R.1    Brown, P.F.2    De Souza, P.V.3    Mercer, R.L.4
  • 30
    • 0036461035 scopus 로고    scopus 로고
    • Large scale discriminative training of hidden Markov models for speech recognition
    • P. C. Woodland and D. Povey, "Large scale discriminative training of hidden Markov models for speech recognition, "Comput. Speech Lang., vol. 16, pp. 25-47, 2002.
    • (2002) Comput. Speech Lang. , vol.16 , pp. 25-47
    • Woodland, P.C.1    Povey, D.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.