Deep architectures for articulatory inversion

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

Volumn 1, Issue , 2012, Pages 866-869

  Uria, Benigno ^a   Murray, Iain ^a   Renals, Steve ^a   Richmond, Korin ^a  

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

Articulatory inversion; Deep belief network; Deep neural network; Deep regression network; Pretraining

Indexed keywords

ACCURATE PREDICTION; ADJUSTABLE PARAMETERS; ARTICULATORY INVERSION; DEEP BELIEF NETWORKS; DEEP NEURAL NETWORKS; INVERSION ACCURACY; PRE-TRAINING; ROOT MEAN SQUARE ERRORS;

MEAN SQUARE ERROR; NEURAL NETWORKS; STATISTICAL TESTS;

NETWORK ARCHITECTURE;

EID: 84878403872     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (23)

1. S. King, J. Frankel, K. Livescu, E. McDermott, K. Richmond, and M. Wester, "Speech production knowledge in automatic speech recognition," Journal of the Acoustical Society of America, vol. 121, pp. 723-743, 2007.
2. Z. Ling, K. Richmond, J. Yamagishi, and R. Wang, "Integrating articulatory features into HMM-based parametric speech synthesis," IEEE Transactions on Audio, Speech and Language Processing, vol. 17, no. 6, pp. 1171-1185, 2009.
3. G. Hofer and K. Richmond, "Comparison of HMM and TMDN methods for lip synchronisation," in Proc. Interspeech, Makuhari, Japan, September 2010, pp. 454-457.
4. K. Richmond, S. King, and P. Taylor, "Modelling the uncertainty in recovering articulation from acoustics," Computer Speech and Language, vol. 17, pp. 153-172, 2003.
5. L. Zhang and S. Renals, "Acoustic-articulatory modeling with the trajectory HMM," IEEE Signal Processing Letters, vol. 15, pp. 245-248, 2008.
6. A. Mohamed, G. E. Dahl, and G. Hinton, "Acoustic modelling using deep belief networks," IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 14-22, 2012.
7. G. E. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition," IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 30-42, 2012.
8. K. Richmond, P. Hoole, and S. King, "Announcing the electromagnetic articulography (day 1) subset of the mngu0 articulatory corpus," in Proc. Interspeech, 2011.
9. K. Richmond, "Preliminary inversion mapping results with a new EMA corpus," in Proc. Interspeech, Brighton, UK, Sep. 2009, pp. 2835-2838.
10. K. Hornik, M. Stinchcombe, and H. White, "Multilayer feedforward networks are universal approximators," Neural Networks, vol. 2, no. 5, pp. 359-366, 1989.
11. Y. Bengio, P. Lamblin, D. Popovici, and H. Larochelle, "Greedy layer-wise training of deep networks," in Advances in Neural Information Processing Systems, vol. 19. Vancouver, Canada: The MIT Press, Dec. 2007, p. 153.
12. Y. Bengio, "Learning deep architectures for AI," Foundations and Trends in Machine Learning, vol. 2, no. 1, pp. 1-127, 2009.
13. F. Grézl, M. Karafiát, and M. Janda, "Study of probabilistic and bottle-neck features in multilingual environment," in Proc. IEEE ASRU, 2011.
14. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription," in Proc. IEEE ASRU, 2011.
15. G. Hinton, S. Osindero, and Y. Teh, "A fast learning algorithm for deep belief nets," Neural Computation, vol. 18, no. 7, pp. 1527-1554, 2006.
16. G. Hinton, "Training products of experts by minimizing contrastive divergence," Neural Computation, vol. 14, no. 8, pp. 1771-1800, 2002.
17. M. Carreira-Perpiñán and G. Hinton, "On contrastive divergence learning," in Proc. Artificial Intelligence and Statistics, 2005, pp. 33-40.
18. K. Richmond, "A trajectory mixture density network for the acoustic-articulatory inversion mapping," in Proc. Interspeech, Pittsburgh, USA, Sep. 2006.
19. C. Bishop, "Mixture density networks," Neural Computing Research Group, Aston University, Tech. Rep. NCRG/94/004, 1994.
20. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, "Speech parameter generation algorithms for HMM-based speech synthesis," in Proc. ICASSP, Istanbul, Turkey, Jun. 2000, pp. 1315-1318.
21. J. Perkell, M. Cohen, M. Svirsky, M. Matthies, I. Garabieta, and M. Jackson, "Electromagnetic midsagittal articulometer systems for transducing speech articulatory movements," The Journal of the Acoustical Society of America, vol. 92, p. 3078, 1992.
22. H. Strube, "Linear prediction on a warped frequency scale," The Journal of the Acoustical Society of America, vol. 68, p. 1071, 1980.
23. K. L. Poort, "Stop consonant production: An articulation and acoustic study," Master's thesis, MIT, 1995.