메뉴 건너뛰기




Volumn , Issue , 2014, Pages 1764-1768

Synthesized stereo mapping via deep neural networks for noisy speech recognition

Author keywords

deep neural network; HMM based speech synthesis; joint Gaussian mixture model; noisy speech recognition

Indexed keywords

SIGNAL PROCESSING; SPEECH RECOGNITION; SPEECH SYNTHESIS; STOCHASTIC SYSTEMS;

EID: 84905284245     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2014.6853901     Document Type: Conference Paper
Times cited : (12)

References (33)
  • 2
    • 34547550766 scopus 로고    scopus 로고
    • Stereo-based stochastic mapping for robust speech recognition
    • M. Afify, X. Cui, and Y. Gao, "Stereo-based stochastic mapping for robust speech recognition," Proc. ICASSP, 2007, pp.377-380.
    • (2007) Proc. ICASSP , pp. 377-380
    • Afify, M.1    Cui, X.2    Gao, Y.3
  • 3
    • 68549125183 scopus 로고    scopus 로고
    • Stereo-based stochastic mapping for robust speech recognition
    • M. Afify, X. Cui, and Y. Gao, "Stereo-based stochastic mapping for robust speech recognition," IEEE Trans. on Audio, Speech and Language Processing, Vol. 17, No. 7, pp.1325-1334, 2009.
    • (2009) IEEE Trans. on Audio, Speech and Language Processing , vol.17 , Issue.7 , pp. 1325-1334
    • Afify, M.1    Cui, X.2    Gao, Y.3
  • 4
    • 84905267603 scopus 로고    scopus 로고
    • Availability of finnish speechdat-car database for etsi stq wi008 front-end standardisation
    • Aurora document AU/217/99, Nov
    • Aurora document AU/217/99, "Availability of Finnish SpeechDat-Car database for ETSI STQ WI008 front-end standardisation," Nokia, Nov. 1999.
    • (1999) Nokia
  • 5
    • 84905249653 scopus 로고    scopus 로고
    • Spanish SDC-Aurora database for ETSI STQ Aurora WI008 advanced DSR front-end evaluation: Description and baseline results
    • Aurora document AU/271/00, Nov
    • Aurora document AU/271/00, "Spanish SDC-Aurora database for ETSI STQ Aurora WI008 advanced DSR front-end evaluation: description and baseline results," UPC, Nov. 2000.
    • (2000) UPC
  • 6
    • 84905267604 scopus 로고    scopus 로고
    • Description and baseline results for the subset of the SpeechDat-Car German database used for ETSI STQ Aurora WI008 advanced DSR front-end evaluation
    • Aurora document AU/273/00, Dec
    • Aurora document AU/273/00, "Description and baseline results for the subset of the SpeechDat-Car German database used for ETSI STQ Aurora WI008 advanced DSR front-end evaluation," Texas Instruments, Dec. 2001.
    • (2001) Texas Instruments
  • 8
    • 4544344467 scopus 로고    scopus 로고
    • Multienvironment models based linear normalization for robust speech recognition in car conditions
    • L. Buera, E. Lleida, A. Miguel, and A. Ortega, "Multienvironment models based linear normalization for robust speech recognition in car conditions," Proc. ICASSP, 2004, pp.1013-1016.
    • (2004) Proc. ICASSP , pp. 1013-1016
    • Buera, L.1    Lleida, E.2    Miguel, A.3    Ortega, A.4
  • 9
    • 33947644350 scopus 로고    scopus 로고
    • Evaluation of the SPACE denoising algorithm on Aurora2
    • C. Cerisara and K. Daoudi, "Evaluation of the SPACE denoising algorithm on Aurora2," Proc. ICASSP, 2006, pp.I-521-I-524.
    • (2006) Proc. ICASSP
    • Cerisara, C.1    Daoudi, K.2
  • 10
    • 84055222005 scopus 로고    scopus 로고
    • Context-dependent pre-trained deep neural networks for large vocabulary speech recognition
    • G. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependent pre-trained deep neural networks for large vocabulary speech recognition," IEEE Trans. on Audio, Speech and Language Processing, Vol. 20, No. 1, pp.30-42, 2012.
    • (2012) IEEE Trans. on Audio, Speech and Language Processing , vol.20 , Issue.1 , pp. 30-42
    • Dahl, G.1    Yu, D.2    Deng, L.3    Acero, A.4
  • 11
    • 20444414457 scopus 로고    scopus 로고
    • Analysis and comparison of two speech feature extraction/compensation algorithms
    • L. Deng, J. Wu, J. Droppo, and A. Acero, "Analysis and comparison of two speech feature extraction/compensation algorithms," IEEE Signal Process. Lett., Vol. 12, No. 6, pp.477-480, 2005.
    • (2005) IEEE Signal Process. Lett. , vol.12 , Issue.6 , pp. 477-480
    • Deng, L.1    Wu, J.2    Droppo, J.3    Acero, A.4
  • 12
    • 85006734596 scopus 로고    scopus 로고
    • Evaluation of the SPLICE algorithm on the Aurora2 database
    • J. Droppo, L. Deng, and A. Acero, "Evaluation of the SPLICE algorithm on the Aurora2 database," Proc. EuroSpeech, 2001, pp.217-220.
    • (2001) Proc. EuroSpeech , pp. 217-220
    • Droppo, J.1    Deng, L.2    Acero, A.3
  • 13
    • 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," Proc. EuroSpeech, 2005, pp.989-992.
    • (2005) Proc. EuroSpeech , pp. 989-992
    • Droppo, J.1    Acero, A.2
  • 14
    • 78049390326 scopus 로고    scopus 로고
    • HMM-based pseudo-clean speech synthesis for SPLICE algorithm
    • J. Du, Y. Hu, L.-R. Dai, and R.-H. Wang, "HMM-based pseudo-clean speech synthesis for SPLICE algorithm," Proc. ICASSP, 2010, pp.4570-4573.
    • (2010) Proc. ICASSP , pp. 4570-4573
    • Du, J.1    Hu, Y.2    Dai, L.-R.3    Wang, R.-H.4
  • 15
    • 84878378712 scopus 로고    scopus 로고
    • IVN-based joint training of GMM and HMMs using an improved VTS-based feature compensation for noisy speech recognition
    • J. Du and Q. Huo, "IVN-based joint training of GMM and HMMs using an improved VTS-based feature compensation for noisy speech recognition," Proc. INTERSPEECH, 2012.
    • (2012) Proc. INTERSPEECH
    • Du, J.1    Huo, Q.2
  • 16
    • 84874472370 scopus 로고    scopus 로고
    • Synthesized stereo-based stochastic mapping with data selection for robust speech recognition
    • J. Du and Q. Huo, "Synthesized stereo-based stochastic mapping with data selection for robust speech recognition," Proc. ISCSLP, 2012, pp.122-125.
    • (2012) Proc. ISCSLP , pp. 122-125
    • Du, J.1    Huo, Q.2
  • 17
    • 0029288202 scopus 로고
    • Speech recognition in noisy environments: A survey
    • Y. Gong, "Speech recognition in noisy environments: A survey," Speech Communication, Vol. 16, No. 3, pp.261-291, 1995.
    • (1995) Speech Communication , vol.16 , Issue.3 , pp. 261-291
    • Gong, Y.1
  • 18
    • 33745805403 scopus 로고    scopus 로고
    • A fast learning algorithm for deep belief nets
    • G. Hinton, S. Osindero, and Y. Teh, "A fast learning algorithm for deep belief nets," Neural Computation, Vol. 18, pp.1527-1554, 2006.
    • (2006) Neural Computation , vol.18 , pp. 1527-1554
    • Hinton, G.1    Osindero, S.2    Teh, Y.3
  • 19
    • 33746600649 scopus 로고    scopus 로고
    • Reducing the dimensionality of data with neural networks
    • G. Hinton and R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, Vol. 313, No. 5786, pp.504-507, 2006.
    • (2006) Science , vol.313 , Issue.5786 , pp. 504-507
    • Hinton, G.1    Salakhutdinov, R.2
  • 22
    • 34547526633 scopus 로고    scopus 로고
    • A maximum likelihood training approach to irrelevant variability compensation based on piecewise linear transformations
    • Q. Huo and D.-L. Zhu, "A maximum likelihood training approach to irrelevant variability compensation based on piecewise linear transformations," Proc. ICSLP, 2006, pp.1129-1132.
    • (2006) Proc. ICSLP , pp. 1129-1132
    • Huo, Q.1    Zhu, D.-L.2
  • 26
    • 84865801985 scopus 로고    scopus 로고
    • Conversational speech transcription using context-dependent deep neural networks
    • F. Seide, Gang Li, and Dong Yu, "Conversational speech transcription using context-dependent deep neural networks," Proc. INTERSPEECH, 2011, pp.437-440.
    • (2011) Proc. INTERSPEECH , pp. 437-440
    • Seide, F.1    Li, G.2    Yu, D.3
  • 27
    • 84890492030 scopus 로고    scopus 로고
    • An investigation of deep neural networks for noise robust speech recognition
    • M. Seltzer, D. Yu, and Y.-Q. Wang, "An investigation of deep neural networks for noise robust speech recognition," Proc. ICASSP, 2013, pp.7398-7402.
    • (2013) Proc. ICASSP , pp. 7398-7402
    • Seltzer, M.1    Yu, D.2    Wang, Y.-Q.3
  • 28
  • 29
    • 44849090158 scopus 로고    scopus 로고
    • An environment-compensated minimum classification error training approach based on stochastic vector mapping
    • J. Wu and Q. Huo, "An environment-compensated minimum classification error training approach based on stochastic vector mapping," IEEE Trans. on Audio, Speech and Language Processing, Vol. 14, No. 6, pp.2147-2155, 2006.
    • (2006) IEEE Trans. on Audio, Speech and Language Processing , vol.14 , Issue.6 , pp. 2147-2155
    • Wu, J.1    Huo, Q.2
  • 30
    • 34547546133 scopus 로고    scopus 로고
    • Word graph based feature enhancement for noisy speech recognition
    • Z.-J. Yan, F. K. Soong, and R.-H. Wang, "Word graph based feature enhancement for noisy speech recognition," Proc. ICASSP, 2007, pp.373-376.
    • (2007) Proc. ICASSP , pp. 373-376
    • Yan, Z.-J.1    Soong, F.K.2    Wang, R.-H.3
  • 31
    • 84905285644 scopus 로고    scopus 로고
    • An experimental study on speech enhancement based on deep neural networks
    • Y. Xu, J. Du, L.-R. Dai, and C.-H. Lee, "An experimental study on speech enhancement based on deep neural networks," Accepted by Signal Processing Letter.
    • Signal Processing Letter
    • Xu, Y.1    Du, J.2    Dai, L.-R.3    Lee, C.-H.4


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.