메뉴 건너뛰기




Volumn , Issue , 2014, Pages 4623-4627

Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition

Author keywords

automatic speech recognition; De reverberation; feature enhancement; recurrent neural networks

Indexed keywords

LEARNING SYSTEMS; RECURRENT NEURAL NETWORKS; SIGNAL PROCESSING; SPEECH RECOGNITION;

EID: 84905216003     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2014.6854478     Document Type: Conference Paper
Times cited : (80)

References (28)
  • 1
    • 84890492030 scopus 로고    scopus 로고
    • An investigation of deep neural networks for noise robust speech recognition
    • Vancouver, Canada
    • M.L. Seltzer, D. Yu, and Y. Wang, "An investigation of deep neural networks for noise robust speech recognition, " in Proc. of ICASSP, Vancouver, Canada, 2013, pp. 7398-7402.
    • (2013) Proc. of ICASSP , pp. 7398-7402
    • Seltzer, M.L.1    Yu, D.2    Wang, Y.3
  • 3
    • 84900537286 scopus 로고    scopus 로고
    • The Munich feature enhancement approach to the 2013 CHiME Challenge using BLSTM recurrent neural networks
    • Vancouver, Canada
    • F. Weninger, J. Geiger, M. Wollmer, B. Schuller, and G. Rigoll, "The Munich feature enhancement approach to the 2013 CHiME Challenge using BLSTM recurrent neural networks, " in Proc. The 2nd CHiME Workshop, Vancouver, Canada, 2013, pp. 86-90.
    • (2013) Proc. The 2nd CHiME Workshop , pp. 86-90
    • Weninger, F.1    Geiger, J.2    Wollmer, M.3    Schuller, B.4    Rigoll, G.5
  • 6
    • 77955671150 scopus 로고    scopus 로고
    • Model-based dereverberation in the Logmelspec domain for robust distant-talking speech recognition
    • Dallas, USA
    • A. Sehr, R. Maas, and W. Kellermann, "Model-based dereverberation in the Logmelspec domain for robust distant-talking speech recognition, " in Proc. of ICASSP, Dallas, USA, 2010, pp. 4298-4301.
    • (2010) Proc. of ICASSP , pp. 4298-4301
    • Sehr, A.1    Maas, R.2    Kellermann, W.3
  • 9
    • 79957856980 scopus 로고    scopus 로고
    • A basis representation of constrained MLLR transforms for robust adaptation
    • D. Povey and K. Yao, "A basis representation of constrained MLLR transforms for robust adaptation, " Computer Speech and Language, vol. 26, pp. 35-51, 2012.
    • (2012) Computer Speech and Language , vol.26 , pp. 35-51
    • Povey, D.1    Yao, K.2
  • 10
    • 70350450398 scopus 로고    scopus 로고
    • Static and dynamic variance compensation for recognition of reverberant speech with dereverberation pre-processing
    • M. Delcroix, T. Nakatani, and S.Watanabe, "Static and dynamic variance compensation for recognition of reverberant speech with dereverberation pre-processing, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 17, no. 2, pp. 324-334, 2009.
    • (2009) IEEE Transactions on Audio, Speech, and Language Processing , vol.17 , Issue.2 , pp. 324-334
    • Delcroix, M.1    Nakatani, T.2    Watanabe, S.3
  • 11
    • 56449089103 scopus 로고    scopus 로고
    • Extracting and composing robust features with denoising autoencoders
    • Helsinki, Finland
    • P. Vincent, H. Larochelle, Y. Bengio, and P. Manzagol, "Extracting and composing robust features with denoising autoencoders, " in Proc. of ICML, Helsinki, Finland, 2008, pp. 1096-1103.
    • (2008) Proc. of ICML , pp. 1096-1103
    • Vincent, P.1    Larochelle, H.2    Bengio, Y.3    Manzagol, P.4
  • 12
    • 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
  • 13
    • 0034293152 scopus 로고    scopus 로고
    • Learning to forget: Continual prediction with LSTM
    • F. 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.1    Schmidhuber, J.2    Cummins, F.3
  • 15
    • 85132941272 scopus 로고    scopus 로고
    • Speech dereverberation using statistical reverberation models
    • P.A. Naylor and N.D. Gaubitch, Eds. Springer
    • E. Habets, "Speech dereverberation using statistical reverberation models, " in Speech Dereverberation, P.A. Naylor and N.D. Gaubitch, Eds., pp. 57-93. Springer, 2010.
    • (2010) Speech Dereverberation , pp. 57-93
    • Habets, E.1
  • 16
    • 84962920708 scopus 로고    scopus 로고
    • Evaluating long-term spectral subtraction for reverberant ASR
    • Madonna di Campiglio, ItalyIEEE
    • D. Gelbart and N. Morgan, "Evaluating long-term spectral subtraction for reverberant ASR, " in Proc. of ASRU, Madonna di Campiglio, Italy, 2001, pp. 103-106, IEEE.
    • (2001) Proc. of ASRU , pp. 103-106
    • Gelbart, D.1    Morgan, N.2
  • 18
    • 84906279378 scopus 로고    scopus 로고
    • Speech enhancement with weighted denoising auto-encoder
    • Lyon, France
    • B.Y. Xia and C.C. Bao, "Speech enhancement with weighted denoising auto-encoder, " in Proc. of INTERSPEECH, Lyon, France, 2013, pp. 436-440.
    • (2013) Proc. of INTERSPEECH , pp. 436-440
    • Xia, B.Y.1    Bao, C.C.2
  • 19
    • 84900542109 scopus 로고    scopus 로고
    • Recurrent neural network feature enhancement: The 2nd CHiME challenge
    • IEEE. Vancouver, Canada, June
    • A.L. Maas, T.M. O'Neil, A.Y. Hannun, and A.Y. Ng, "Recurrent neural network feature enhancement: The 2nd CHiME challenge, " in Proc. The 2nd CHiME Workshop, Vancouver, Canada, June 2013, pp. 79-80, IEEE.
    • (2013) Proc. The 2nd CHiME Workshop , pp. 79-80
    • Maas, A.L.1    O'neil, T.M.2    Hannun, A.Y.3    Ng, A.Y.4
  • 20
    • 84877253028 scopus 로고    scopus 로고
    • Dereverberation method with reverberation time estimation using floored ratio of spectral subtraction
    • Y. Tachioka, T. Hanazawa, and T. Iwasaki, "Dereverberation method with reverberation time estimation using floored ratio of spectral subtraction, " Acoustical Science and Technology, vol. 34, no. 3, pp. 212-215, 2013.
    • (2013) Acoustical Science and Technology , vol.34 , Issue.3 , pp. 212-215
    • Tachioka, Y.1    Hanazawa, T.2    Iwasaki, T.3
  • 21
    • 0018455310 scopus 로고
    • Suppression of acoustic noise in speech using spectral subtraction
    • S.F. Boll, "Suppression of acoustic noise in speech using spectral subtraction, " IEEE Transactions on Acoustics, Speech and Signal Processing, vol. 27, no. 2, pp. 113-120, 1979.
    • (1979) IEEE Transactions on Acoustics, Speech and Signal Processing , vol.27 , Issue.2 , pp. 113-120
    • Boll, S.F.1
  • 22
    • 84890543083 scopus 로고    scopus 로고
    • Speech recognition with deep recurrent neural networks
    • Vancouver, Canada, May, IEEE
    • A. Graves, A. Mohamed, and G. Hinton, "Speech recognition with deep recurrent neural networks, " in Proc. of ICASSP, Vancouver, Canada, May 2013, pp. 6645-6649, IEEE.
    • (2013) Proc. of ICASSP , pp. 6645-6649
    • Graves, A.1    Mohamed, A.2    Hinton, G.3
  • 23
    • 84865791631 scopus 로고    scopus 로고
    • Speech-based non-prototypical affect recognition for childrobot interaction in reverberated environments
    • Florence, Italy
    • M.Wollmer, F.Weninger, S. Steidl, A. Batliner, and B. Schuller, "Speech-based non-prototypical affect recognition for childrobot interaction in reverberated environments, " in Proc. of INTERSPEECH, Florence, Italy, 2011, pp. 3113-3116.
    • (2011) Proc. of INTERSPEECH , pp. 3113-3116
    • Wollmer, M.1    Weninger, F.2    Steidl, S.3    Batliner, A.4    Schuller, B.5
  • 24
    • 0028996854 scopus 로고
    • WSJCAM0: A British English speech corpus for large vocabulary continuous speech recognition
    • Detroit, MI, USA
    • T. Robinson, J. Fransen, D. Pye, J. Foote, and S. Renals, "WSJCAM0: A British English speech corpus for large vocabulary continuous speech recognition, " in Proc. of ICASSP, Detroit, MI, USA, 1995, pp. 81-84.
    • (1995) Proc. of ICASSP , pp. 81-84
    • Robinson, T.1    Fransen, J.2    Pye, D.3    Foote, J.4    Renals, S.5
  • 27
    • 0032638856 scopus 로고    scopus 로고
    • Semi-tied covariance matrices for hidden Markov models
    • M. Gales, "Semi-tied covariance matrices for hidden Markov models, " IEEE Transactions on Speech and Audio Processing, vol. 7, pp. 272-281, 1999.
    • (1999) IEEE Transactions on Speech and Audio Processing , vol.7 , pp. 272-281
    • Gales, M.1
  • 28
    • 84890503970 scopus 로고    scopus 로고
    • Effectiveness of discriminative training and feature transformation for reverberated and noisy speech
    • Vancouver, Canada
    • Y. Tachioka, S. Watanabe, and J.R. Hershey, "Effectiveness of discriminative training and feature transformation for reverberated and noisy speech, " in Proc. of ICASSP, Vancouver, Canada, 2013, pp. 6935-6939
    • (2013) Proc. of ICASSP , pp. 6935-6939
    • Tachioka, Y.1    Watanabe, S.2    Hershey, J.R.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.