메뉴 건너뛰기




Volumn , Issue , 2013, Pages 6935-6939

Effectiveness of discriminative training and feature transformation for reverberated and noisy speech

Author keywords

Augmented discriminative feature transformation; CHiME challenge; Discriminative training; Feature transformation; Kaldi

Indexed keywords

CHIME CHALLENGE; DISCRIMINATIVE FEATURES; DISCRIMINATIVE TRAINING; FEATURE TRANSFORMATIONS; KALDI;

EID: 84890503970     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6639006     Document Type: Conference Paper
Times cited : (13)

References (26)
  • 2
    • 85032750905 scopus 로고    scopus 로고
    • Discriminative learning in sequential pattern recognition
    • September
    • X. He, L. Deng, and W. Chou, "Discriminative learning in sequential pattern recognition," IEEE Signal Processing Magazine, vol. 25, pp. 14-36, September 2008
    • (2008) IEEE Signal Processing Magazine , vol.25 , pp. 14-36
    • He, X.1    Deng, L.2    Chou, W.3
  • 3
    • 0022890536 scopus 로고
    • Maximum mutual information estimation of hidden Markov model parameters for speech recognition
    • L. Bahl, P. Brown, P. de Souza, and R. Mercer "Maximum mutual information estimation of hidden Markov model parameters for speech recognition," in Proceedings ICASSP. IEEE, 1986, pp. 49-52
    • (1986) Proceedings ICASSP. IEEE , pp. 49-52
    • Bahl, L.1    Brown, P.2    De Souza, P.3    Mercer, R.4
  • 4
    • 0036296863 scopus 로고    scopus 로고
    • Minimum phone error and Ismoothing for improved discriminative training
    • D. Povey, and P.C. Woodland, "Minimum phone error and Ismoothing for improved discriminative training," in Proceedings ICASSP. IEEE, 2002, pp. 105-108
    • (2002) Proceedings ICASSP. IEEE , pp. 105-108
    • Povey, D.1    Woodland, P.C.2
  • 6
    • 78049409757 scopus 로고    scopus 로고
    • Discriminative training based on an integrated view of MPE and MMI in margin and error space
    • E. McDermott, S. Watanabe, and A. Nakamura, "Discriminative training based on an integrated view of MPE and MMI in margin and error space," in Proceedings ICASSP. IEEE, 2010, pp. 4894-4897
    • (2010) Proceedings ICASSP. IEEE , pp. 4894-4897
    • McDermott, E.1    Watanabe, S.2    Nakamura, A.3
  • 7
    • 85017287487 scopus 로고
    • Linear discriminant analysis for improved large vocabulary continuous speech recognition
    • R. Haeb-Umbach and H. Ney, "Linear discriminant analysis for improved large vocabulary continuous speech recognition," in Proceedings ICASSP. IEEE, 1992, pp. 13-16
    • (1992) Proceedings ICASSP. IEEE , pp. 13-16
    • Haeb-Umbach, R.1    Ney, H.2
  • 8
    • 84892187452 scopus 로고    scopus 로고
    • Maximum likelihood modeling with Gaussian distributions for classification
    • R.A. Gopinath, "Maximum likelihood modeling with Gaussian distributions for classification," in Proceedings ICASSP. IEEE, 1998, pp. 661-664
    • (1998) Proceedings ICASSP. IEEE , pp. 661-664
    • Gopinath, R.A.1
  • 9
    • 0032638856 scopus 로고    scopus 로고
    • Semi-tied covariance matrices for hidden Markov models
    • July
    • M.J.F. Gales, "Semi-tied covariance matrices for hidden Markov models," IEEE Transactions on Speech and Audio Processing, vol. 7, pp. 272-281, July 1999
    • (1999) IEEE Transactions on Speech and Audio Processing , vol.7 , pp. 272-281
    • Gales, M.J.F.1
  • 13
    • 33745211419 scopus 로고    scopus 로고
    • Improvements to fMPE for discriminative training of features
    • D. Povey, "Improvements to fMPE for discriminative training of features," in Proceedings INTERSPEECH. ISCA, 2005, pp. 2977-2980
    • (2005) Proceedings INTERSPEECH. ISCA , pp. 2977-2980
    • Povey, D.1
  • 14
    • 33745216251 scopus 로고    scopus 로고
    • Maximum mutual information SPLICE transform for seen and unseen conditions
    • J. Droppo and A. Acero, "Maximum mutual information SPLICE transform for seen and unseen conditions," in Proceedings INTERSPEECH. ISCA, 2005, pp. 989-992
    • (2005) Proceedings INTERSPEECH. ISCA , pp. 989-992
    • Droppo, J.1    Acero, A.2
  • 15
    • 44949102463 scopus 로고    scopus 로고
    • Recent progress on the discriminative region-dependent transform for speech feature extraction
    • B. Zhang, S. Matsoukas, and R. Schwartz, "Recent progress on the discriminative region-dependent transform for speech feature extraction," in Proceedings INTERSPEECH. ISCA, 2006. pp. 1573-1576
    • (2006) Proceedings INTERSPEECH. ISCA , pp. 1573-1576
    • Zhang, B.1    Matsoukas, S.2    Schwartz, R.3
  • 17
    • 33745219155 scopus 로고    scopus 로고
    • Regularizing linear discriminant analysis for speech recognition
    • H. Erdo?gan, "Regularizing linear discriminant analysis for speech recognition," in Proceedings INTERSPEECH. ISCA, 2005, pp. 3021-3024
    • (2005) Proceedings INTERSPEECH. ISCA , pp. 3021-3024
    • Erdogan, H.1
  • 18
    • 44849090969 scopus 로고    scopus 로고
    • Recognition and understanding of meetings the AMI and AMIDA projects
    • S. Renals, T. Hain, and H. Bourlard, "Recognition and understanding of meetings the AMI and AMIDA projects," in Proceedings ASRU. IEEE, 2007, pp. 238-247
    • (2007) Proceedings ASRU. IEEE , pp. 238-247
    • Renals, S.1    Hain, T.2    Bourlard, H.3
  • 23
    • 0034848926 scopus 로고    scopus 로고
    • Tandem acoustic modeling in large-vocabulary recognition
    • D. Ellis, R. Singh, and S. Sivadas, "Tandem acoustic modeling in large-vocabulary recognition," in Proceedings ICASSP. IEEE, 2001, pp. 517-520
    • (2001) Proceedings ICASSP. IEEE , pp. 517-520
    • Ellis, D.1    Singh, R.2    Sivadas, S.3
  • 25
    • 0032762471 scopus 로고    scopus 로고
    • A statistical model-based voice activity detection
    • January
    • J. Sohn, N.S. Kim, and W. Sung, "A statistical model-based voice activity detection," IEEE Signal Processing Letters, vol. 6, pp. 1-3, January 1999
    • (1999) IEEE Signal Processing Letters , vol.6 , pp. 1-3
    • Sohn, J.1    Kim, N.S.2    Sung, W.3
  • 26
    • 78650016939 scopus 로고    scopus 로고
    • Underdetermined convolutive blind source separation via frequency bin-wise clustering and permutation alignment
    • March
    • H. Sawada, S. Araki, and S. Makino, "Underdetermined convolutive blind source separation via frequency bin-wise clustering and permutation alignment," IEEE Transactions on Audio, Speech, and Language Processing, vol. 19, pp. 516-527, March 2011.
    • (2011) IEEE Transactions on Audio, Speech, and Language Processing , vol.19 , pp. 516-527
    • Sawada, H.1    Araki, S.2    Makino, S.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.