메뉴 건너뛰기




Volumn , Issue , 2013, Pages 1297-1301

Relevance-weighted-reconstruction of articulatory features in deep-neural-network-based acoustic-to-articulatory mapping

Author keywords

Acoustic to articulatory mapping; Critical articulators; Deep neural networks; Phone recognition

Indexed keywords

TELEPHONE SETS;

EID: 84906219170     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (16)

References (17)
  • 1
    • 84874241818 scopus 로고    scopus 로고
    • Deeplevel acoustic-to-articulatory mapping for DBN-HMM based phone recognition
    • Miami, Florida
    • Badino, L., Canevari, C., Fadiga, L., Metta, G., "Deeplevel acoustic-to-articulatory mapping for DBN-HMM based phone recognition", in Proceedings of IEEE SLT 2012, Miami, Florida, 2012.
    • (2012) Proceedings of IEEE SLT 2012
    • Badino, L.1    Canevari, C.2    Fadiga, L.3    Metta, G.4
  • 2
    • 0004113976 scopus 로고
    • Mixture density networks
    • Department of Computer Science, Aston University, Birmingham, B4 7 ET, UK, February
    • Bishop, C. M., "Mixture density networks", Technical Report NCRG/4288, Neural Computing research Group, Department of Computer Science, Aston University, Birmingham, B4 7 ET, UK, February, 1994.
    • (1994) Technical Report NCRG/4288, Neural Computing Research Group
    • Bishop, C.M.1
  • 3
    • 33846516584 scopus 로고    scopus 로고
    • Springer Science+Business Media, LLC, 233 Spring street, New York, NY 10012, USA
    • Bishop, C. M., "Pattern recognition and machine learning", Springer Science+Business Media, LLC, 233 Spring street, New York, NY 10012, USA, 2009.
    • (2009) Pattern Recognition and Machine Learning
    • Bishop, C.M.1
  • 4
    • 33745805403 scopus 로고    scopus 로고
    • A fast learning algorithm for deep belief nets
    • Hinton, G. E., Osindero, S. and Teh, Y., "A fast learning algorithm for deep belief nets", Neural Computation, 18, pp 1527- 1554, 2006.
    • (2006) Neural Computation , vol.18 , pp. 1527-1554
    • Hinton, G.E.1    Osindero, S.2    Teh, Y.3
  • 6
    • 0002539638 scopus 로고
    • Formant frequencies of some fixed-mandible vowels and model of speech motor programming by predictive simulation
    • Lindblom, B., Lubker, J. and Gay, T., "Formant frequencies of some fixed-mandible vowels and model of speech motor programming by predictive simulation", Journal of Phonetics, vol. 7, pp. 146-161, 1979.
    • (1979) Journal of Phonetics , vol.7 , pp. 146-161
    • Lindblom, B.1    Lubker, J.2    Gay, T.3
  • 7
    • 29444436962 scopus 로고    scopus 로고
    • Integration of articulatory and spectrum features based on the hybrid HMM/BN modelling framework
    • Markov, K., Dang, J. and Nakamura, S., "Integration of articulatory and spectrum features based on the hybrid HMM/BN modelling framework", Speech Communication, vol. 48, 161-175, 2006.
    • (2006) Speech Communication , vol.48 , pp. 161-175
    • Markov, K.1    Dang, J.2    Nakamura, S.3
  • 10
    • 0026675669 scopus 로고
    • Inferring articulation and recognising gestures from acoustics with a neural network trained on x-ray microbeam data
    • Papcun, G., Hochberg, J., Thomas, T. R., Laroche, F., Zachs, J. and Levy, S., "Inferring Articulation and Recognising Gestures from Acoustics with a Neural Network Trained on X-ray Microbeam Data", The Journal of the Acoustical Society of America, 92(2), pp. 688-700, 1992.
    • (1992) The Journal of the Acoustical Society of America , vol.92 , Issue.2 , pp. 688-700
    • Papcun, G.1    Hochberg, J.2    Thomas, T.R.3    Laroche, F.4    Zachs, J.5    Levy, S.6
  • 11
    • 0038359547 scopus 로고    scopus 로고
    • Modeling the uncertainty in recovering articulation from acoustics
    • Richmond, K., King, S. and Taylor, P., "Modeling the uncertainty in recovering articulation from acoustics", Computer Speech and Language, vol. 17(2), pp. 153-172, 2003.
    • (2003) Computer Speech and Language , vol.17 , Issue.2 , pp. 153-172
    • Richmond, K.1    King, S.2    Taylor, P.3
  • 12
    • 0030008004 scopus 로고    scopus 로고
    • The potential role of speech production models in automatic speech recognition
    • Rose, R. C., Schroeter, J. and Sondhi, M. M., "The potential role of speech production models in automatic speech recognition", The Journal of the Acoustical Society of America, 99(3), pp. 1699-1709, 1996.
    • (1996) The Journal of the Acoustical Society of America , vol.99 , Issue.3 , pp. 1699-1709
    • Rose, R.C.1    Schroeter, J.2    Sondhi, M.M.3
  • 14
    • 84878403872 scopus 로고    scopus 로고
    • Deep architectures for articulatory inversion
    • Portland, Orego, USA, September
    • Uria, B., Murray, I., Renals, S., Richmond, K., "Deep architectures for articulatory inversion", In Proc. Interspeech, Portland, Orego, USA, September 2012.
    • (2012) Proc. Interspeech
    • Uria, B.1    Murray, I.2    Renals, S.3    Richmond, K.4
  • 16
    • 84906213644 scopus 로고    scopus 로고
    • Available at http://data.cstr.ed.ac.uk/mocha/.
  • 17
    • 84906245796 scopus 로고    scopus 로고
    • Available at http://htk.eng.cam.ac.uk/.


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.