메뉴 건너뛰기




Volumn 2015-January, Issue , 2015, Pages 3600-3604

Training deep bidirectional LSTM acoustic model for LVCSR by a context-sensitive-chunk BPTT approach

Author keywords

BPTT; Context sensitive chunk; DBLSTM; DNN; Long short term memory; LVCSR

Indexed keywords

BRAIN; CONTINUOUS SPEECH RECOGNITION; SPEECH COMMUNICATION;

EID: 84959076031     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (19)

References (30)
  • 1
    • 0028392167 scopus 로고
    • An application of recurrent nets to phone proba-bility estimation
    • A. J. Robinson, "An application of recurrent nets to phone proba-bility estimation, " IEEE Transactions on Neural Networks, vol. 5, no. 2, pp. 298-305, 1994.
    • (1994) IEEE Transactions on Neural Networks , vol.5 , Issue.2 , pp. 298-305
    • Robinson, A.J.1
  • 2
    • 0001592322 scopus 로고    scopus 로고
    • The use of recurrentneural networks in continuous speech recognition
    • C.-H. Lee, F. Soong, and K. Paliwal (Eds.)
    • T. Robinson, M. Hochberg, and S. Renals, "The use of recurrentneural networks in continuous speech recognition, " in C.-H. Lee, F. Soong, and K. Paliwal (Eds.), Automatic Speech and SpeakerRecognition, pp. 233-258, 1996.
    • (1996) Automatic Speech and SpeakerRecognition , pp. 233-258
    • Robinson, T.1    Hochberg, M.2    Renals, S.3
  • 6
    • 0031573117 scopus 로고    scopus 로고
    • Long short-term memory
    • S. Hochreiter, and J. Schmidhuber, "Long short-term memory, "Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.
    • (1997) Neural Computation , vol.9 , Issue.8 , pp. 1735-1780
    • Hochreiter, S.1    Schmidhuber, J.2
  • 7
    • 0034293152 scopus 로고    scopus 로고
    • Learning to forget: Continual prediction with LSTM
    • F. A. Gers, J. Schmidhuber, and F. Cummins, "Learning to forget: continual prediction with LSTM, " Neural Computation, vol. 12, no. 10, pp. 2451-2471, 2000.
    • (2000) Neural Computation , vol.12 , Issue.10 , pp. 2451-2471
    • Gers, F.A.1    Schmidhuber, J.2    Cummins, F.3
  • 9
    • 27744588611 scopus 로고    scopus 로고
    • Framewise phoneme classifica-tion with bidirectional LSTM and other neural network architec-tures
    • A. Graves, and J. Schmidhuber, "Framewise phoneme classifica-tion with bidirectional LSTM and other neural network architec-tures, " Neural Networks vol. 18, no. 5, pp. 602-610, 2005.
    • (2005) Neural Networks , vol.18 , Issue.5 , pp. 602-610
    • Graves, A.1    Schmidhuber, J.2
  • 10
    • 33646258991 scopus 로고    scopus 로고
    • BidirectionalLSTM networks for improved phoneme classification and recog-nition
    • Springer LNCS 3697
    • A. Graves, S. Fernánd ez and J. Schmidhuber, "BidirectionalLSTM networks for improved phoneme classification and recog-nition, " Proc. ICANN-2005, Springer LNCS 3697, pp. 799-804.
    • Proc. ICANN-2005 , pp. 799-804
    • Graves, A.1    Fernánd Ez, S.2    Schmidhuber, J.3
  • 12
    • 34250704813 scopus 로고    scopus 로고
    • Con-nectionist temporal classification: Labelling unsegmented sequencedata with recurrent neural networks
    • A. Graves, S. Fernánd ez, F. Gomez, and J. Schmidhuber "Con-nectionist temporal classification: labelling unsegmented sequencedata with recurrent neural networks, " Proc. ICML-2006, pp. 369-376.
    • Proc. ICML-2006 , pp. 369-376
    • Graves, A.1    Fernánd Ez, S.2    Gomez, F.3    Schmidhuber, J.4
  • 13
    • 84890543083 scopus 로고    scopus 로고
    • Speech recogni-tion with deep recurrent neural networks
    • A. Graves, A. R. Mohamed, and G. Hinton, "Speech recogni-tion with deep recurrent neural networks, " Proc. ICASSP-2013, pp. 6645-6649.
    • Proc. ICASSP-2013 , pp. 6645-6649
    • Graves, A.1    Mohamed, A.R.2    Hinton, G.3
  • 14
    • 84936143793 scopus 로고    scopus 로고
    • Towards end-to-end speech recognitionwith recurrent neural networks
    • A. Graves, and N. Jaitly, "Towards end-to-end speech recognitionwith recurrent neural networks, " Proc. ICML-2014, pp. 1764-1772.
    • (2014) Proc. ICML , pp. 1764-1772
    • Graves, A.1    Jaitly, N.2
  • 16
    • 84893701254 scopus 로고    scopus 로고
    • Hybrid speech recog-nition with deep bidirectional LSTM
    • A. Graves, N. Jaitly, and A. R. Mohamed, "Hybrid speech recog-nition with deep bidirectional LSTM, " Proc. ASRU-2013, pp. 273-278.
    • Proc. ASRU-2013 , pp. 273-278
    • Graves, A.1    Jaitly, N.2    Mohamed, A.R.3
  • 17
    • 84910046405 scopus 로고    scopus 로고
    • Long short-term memory re-current neural network architectures for large scale acoustic mod-eling
    • H. Sak, A. Senior, and F. Beaufays, "Long short-term memory re-current neural network architectures for large scale acoustic mod-eling, " Proc. INTERSPEECH-2014, pp. 338-342.
    • Proc. INTERSPEECH-2014 , pp. 338-342
    • Sak, H.1    Senior, A.2    Beaufays, F.3
  • 19
    • 0001609567 scopus 로고
    • An efficient gradient-based algo-rithm for on-line training of recurrent network trajectories
    • R. J. Williams, and J. Peng, "An efficient gradient-based algo-rithm for on-line training of recurrent network trajectories, " NeuralComputation, vol. 2, no. 4, pp. 490-501, 1990.
    • (1990) NeuralComputation , vol.2 , Issue.4 , pp. 490-501
    • Williams, R.J.1    Peng, J.2
  • 21
    • 84962501970 scopus 로고    scopus 로고
    • A context-sensitive-chunkBPTT approach to training deep LSTM/BLSTM recurrent neuralnetworks for offline hand writing recognition
    • K. Chen, Z.-J. Yan, and Q. Huo, "A context-sensitive-chunkBPTT approach to training deep LSTM/BLSTM recurrent neuralnetworks for offline hand writing recognition, " Proc. ICDAR-2015.
    • Proc. ICDAR-2015
    • Chen, K.1    Yan, Z.-J.2    Huo, Q.3
  • 22
    • 84942251167 scopus 로고    scopus 로고
    • Fast and robust trainingof recurrent neural networks for offline hand writing recognition
    • P. Doetsch, M. Kozielski, and H. Ney, "Fast and robust trainingof recurrent neural networks for offline hand writing recognition, "Proc. ICFHR-2014, pp. 279-284.
    • Proc. ICFHR-2014 , pp. 279-284
    • Doetsch, P.1    Kozielski, M.2    Ney, H.3
  • 24
    • 84887388950 scopus 로고    scopus 로고
    • An em-pirical study of learning rates in deep neural networks for speechrecognition
    • A. Senior, G. Heigold, M. A. Ranzato, and K. Yang, "An em-pirical study of learning rates in deep neural networks for speechrecognition, " Proc. ICASSP-2013, pp. 6724-6728.
    • Proc. ICASSP-2013 , pp. 6724-6728
    • Senior, A.1    Heigold, G.2    Ranzato, M.A.3    Yang, K.4
  • 25
    • 84905233897 scopus 로고    scopus 로고
    • Mean-normalized stochastic gradient for large-scale deep learning
    • S. Wiesler, A. Richard, R. Schluter, and H. Ney, "Mean-normalized stochastic gradient for large-scale deep learning, " Proc. ICASSP-2014, pp. 180-184.
    • Proc. ICASSP-2014 , pp. 180-184
    • Wiesler, S.1    Richard, A.2    Schluter, R.3    Ney, H.4
  • 26
    • 85016587886 scopus 로고    scopus 로고
    • Switch-board: Telephone speech corpus for research and development
    • J. J. Godfrey, Edward. C. Holliman, and J. McDaniel, "Switch-board: telephone speech corpus for research and development, "Proc. ICASSP-1992, pp. I-517-520.
    • Proc. ICASSP-1992 , pp. I517-520
    • Godfrey, J.J.1    Holliman, E.C.2    McDaniel, J.3
  • 28
    • 84865801985 scopus 로고    scopus 로고
    • Conversational speech tran-scription using context-dependent deep neural networks
    • F. Seide, G. Li, and D. Yu, "Conversational speech tran-scription using context-dependent deep neural networks, " Proc. INTERSPEECH-2011, pp. 437-440.
    • Proc. INTERSPEECH-2011 , pp. 437-440
    • Seide, F.1    Li, G.2    Yu, D.3
  • 29
    • 84906225757 scopus 로고    scopus 로고
    • A scalable approach to usingDNN-derived features in GMM-HMM based acoustic modeling forLVCSR
    • Z.-J. Yan, Q. Huo, and J. Xu, "A scalable approach to usingDNN-derived features in GMM-HMM based acoustic modeling forLVCSR, " Proc. INTERSPEECH-2013, pp. 104-108.
    • Proc. INTERSPEECH-2013 , pp. 104-108
    • Yan, Z.-J.1    Huo, Q.2    Xu, J.3
  • 30
    • 0030121298 scopus 로고    scopus 로고
    • A study on the use of bi-directional contex-tual dependence in Markov rand om field-based acoustic modellingfor speech recognition
    • Q. Huo and C. Chan, "A study on the use of bi-directional contex-tual dependence in Markov rand om field-based acoustic modellingfor speech recognition, " Computer Speech and Language, vol. 10, pp. 95-105, 1996.
    • (1996) Computer Speech and Language , vol.10 , pp. 95-105
    • Huo, Q.1    Chan, C.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.