메뉴 건너뛰기




Volumn , Issue , 2014, Pages 6849-6853

Improving deep neural networks for LVCSR using dropout and shrinking structure

Author keywords

deep neural networks; DNN HMM; dropout; dropout as pre conditioner (DAP); LVCSR; shrinking hidden layer

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; HIDDEN MARKOV MODELS; SHRINKAGE;

EID: 84905252086     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2014.6854927     Document Type: Conference Paper
Times cited : (35)

References (21)
  • 1
    • 84865801985 scopus 로고    scopus 로고
    • Conversational speech transcription using context-dependent deep neural networks
    • F. Seide, G. Li, and D. Yu, "Conversational speech transcription using context-dependent deep neural networks.," in INTERSPEECH, 2011, pp. 437-440.
    • (2011) INTERSPEECH , pp. 437-440
    • Seide, F.1    Li, G.2    Yu, D.3
  • 2
    • 84055222005 scopus 로고    scopus 로고
    • Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition
    • G. E. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition," Audio, Speech, and Language Processing, IEEE Transactions on, vol. 20, no. 1, pp. 30-42, 2012.
    • (2012) Audio, Speech, and Language Processing, IEEE Transactions on , vol.20 , Issue.1 , pp. 30-42
    • Dahl, G.E.1    Yu, D.2    Deng, L.3    Acero, A.4
  • 3
    • 84858976070 scopus 로고    scopus 로고
    • Feature engineering in context-dependent deep neural networks for conversational speech transcription
    • F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription," in ASRU. IEEE, 2011, pp. 24-29.
    • (2011) ASRU. IEEE , pp. 24-29
    • Seide, F.1    Li, G.2    Chen, X.3    Yu, D.4
  • 7
    • 33745805403 scopus 로고    scopus 로고
    • A fast learning algorithm for deep belief nets
    • G. E. Hinton, S. Osindero, and Y.-W. Teh, "A fast learning algorithm for deep belief nets," Neural computation, vol. 18, no. 7, pp. 1527-1554, 2006.
    • (2006) Neural Computation , vol.18 , Issue.7 , pp. 1527-1554
    • Hinton, G.E.1    Osindero, S.2    Teh, Y.-W.3
  • 12
    • 84906273501 scopus 로고    scopus 로고
    • Improving low-resource cddnnhmm using dropout and multilingual dnn training
    • Yajie Miao and Florian Metze, "Improving low-resource cddnnhmm using dropout and multilingual dnn training," in Proc. Interspeech, 2013, pp. 2237-2241.
    • (2013) Proc. Interspeech , pp. 2237-2241
    • Miao, Y.1    Metze, F.2
  • 13
    • 84890527827 scopus 로고    scopus 로고
    • Improving deep neural networks for LVCSR using rectified linear units and dropout
    • G. E. Dahl, T. N. Sainath, and G. E. Hinton, "Improving deep neural networks for LVCSR using rectified linear units and dropout," in ICASSP, 2013.
    • (2013) ICASSP
    • Dahl, G.E.1    Sainath, T.N.2    Hinton, G.E.3
  • 14
    • 84890445398 scopus 로고    scopus 로고
    • Understanding the dropout strategy and analyzing its effectiveness on LVCSR
    • J. Li, X. Wang, and B. Xu, "Understanding the dropout strategy and analyzing its effectiveness on LVCSR," in ICASSP, 2013.
    • (2013) ICASSP
    • Li, J.1    Wang, X.2    Xu, B.3
  • 15
    • 84867606668 scopus 로고    scopus 로고
    • Exploiting sparseness in deep neural networks for large vocabulary speech recognition
    • D. Yu, F. Seide, G. Li, and L. Deng, "Exploiting sparseness in deep neural networks for large vocabulary speech recognition," in ICASSP. IEEE, 2012, pp. 4409-4412.
    • (2012) ICASSP. IEEE , pp. 4409-4412
    • Yu, D.1    Seide, F.2    Li, G.3    Deng, L.4
  • 16
    • 84890454527 scopus 로고    scopus 로고
    • Low-rank matrix factorization for deep neural network training with high-dimensional output targets
    • T. N. Sainath, B. Kingsbury, V. Sindhwani, E. Arisoy, and B. Ramabhadran, "Low-rank matrix factorization for deep neural network training with high-dimensional output targets," in ICASSP. IEEE, 2013.
    • (2013) ICASSP. IEEE
    • Sainath, T.N.1    Kingsbury, B.2    Sindhwani, V.3    Arisoy, E.4    Ramabhadran, B.5
  • 17
    • 84906227589 scopus 로고    scopus 로고
    • Restructuring of deep neural network acoustic models with singular value decomposition
    • J. Xue, J. Y. Li, and Y. F. Gong, "Restructuring of deep neural network acoustic models with singular value decomposition," in INTERSPEECH, 2013.
    • (2013) INTERSPEECH
    • Xue, J.1    Li, J.Y.2    Gong, Y.F.3
  • 19
    • 79551480483 scopus 로고    scopus 로고
    • Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
    • P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, and P. Manzagol, "Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion," The Journal of Machine Learning Research, vol. 9999, pp. 3371-3408, 2010.
    • (2010) The Journal of Machine Learning Research , vol.9999 , pp. 3371-3408
    • Vincent, P.1    Larochelle, H.2    Lajoie, I.3    Bengio, Y.4    Manzagol, P.5
  • 20
    • 84876477729 scopus 로고    scopus 로고
    • Investigation on dimensionality reduction of concatenated features with deep neural network for LVCSR systems
    • Y. B. Bao, H. Jiang, C. Liu, Y. Hu, and L. R. Dai, "Investigation on dimensionality reduction of concatenated features with deep neural network for LVCSR systems," in 11th International Conference on Signal Processing (ICSP), 2012, vol. 1, pp. 562-566.
    • (2012) 11th International Conference on Signal Processing (ICSP) , vol.1 , pp. 562-566
    • Bao, Y.B.1    Jiang, H.2    Liu, C.3    Hu, Y.4    Dai, L.R.5


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.