A deep recurrent approach for acoustic-to-articulatory inversion

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 2015-August, Issue , 2015, Pages 4450-4454

  Liu, Peng ^a   Yu, Quanjie ^a   Wu, Zhiyong ^a,b   Kang, Shiyin ^a   Meng, Helen ^a,b   Cai, Lianhong ^a  

^a TSINGHUA UNIVERSITY   (China)

^b CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

layer wise pre training; long short term memory (LSTM); mixture density network (MDN); recurrent nueral network (RNN)

Indexed keywords

AUDIO SIGNAL PROCESSING; BRAIN; DEEP NEURAL NETWORKS; MEAN SQUARE ERROR; MIXTURES; SPEECH COMMUNICATION;

ACCURATE PREDICTION; ARTICULATORY INVERSION; CONTEXT INFORMATION; INVERSION ACCURACY; MIXTURE DENSITY; NUERAL NETWORKS; PRE-TRAINING; ROOT MEAN SQUARE ERRORS;

LONG SHORT-TERM MEMORY;

EID: 84946016986     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2015.7178812     Document Type: Conference Paper

References (25)

1. S. King, J. Frankel, K. Livescu, E. McDermott, K. Richmond, and M. Wester, Speech production knowledge in automatic speech recognition, The Journal of the Acoustical Society of America, vol. 121, no. 2, pp. 723-742, 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. J.H. Zhao, H. Yuan, W.K. Leung, H. Meng, J. Liu, and S.H. Xia, Audiovisual synthesis of exaggerated speech for corrective feedback in computer-assisted pronunciation training, in Proc. ICASSP, 2013, pp. 8218-8222
4. K. Richmond, S. King, and P. Taylor, Modelling the uncertainty in recovering articulation from acoustics, Computer Speech &Language, vol. 17, no. 2, 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. K. Richmond, A trajectory mixture density network for the acoustic-articulatory inversion mapping, in Proc. INTERSPEECH, 2006, pp. 577-580
7. B. Uria, I. Murray, S. Renals, and K. Richmond, Deep architectures for articulatory inversion, in Proc. INTERSPEECH, 2012, pp. 867-870
8. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, Speech parameter generation algorithms for HMMbased speech synthesis, in Proc. ICASSP, 2000, pp. 1315-1318
9. S. Kang, X. Qian, and H. Meng, Multi-distribution deep belief network for speech synthesis, in Proc. ICASSP, 2013, pp. 8012-8016
10. S. Kang and H. Meng, Statistical parametric speech synthesis using weighted multi-distribution deep belief network, in Proc. INTERSPEECH, 2014, pp. 1959-1963
11. H. Zen, A. Senior, and M. Schuster, Statistical parametric speech synthesis using deep neural networks, in Proc. ICASSP, 2013, pp. 7962-7966
12. Z. Ling, L. Deng, and D. Yu, Modeling spectral envelopes using restricted boltzmann machines for statistical parametric speech synthesis, in Proc. ICASSP, 2013, pp. 7825-7829
13. Y. Fan, Y. Qian, F. Xie, and F.K. Soong, TTS synthesis with bidirectional LSTM based recurrent neural networks, in Proc. INTERSPEECH, 2014, pp. 1964-1968
14. M. Schuster and K.K. Paliwal, Bidirectional recurrent neural networks, IEEE Transactions on Signal Processing, pp. 2673-2681, 1997
15. S. Hochreiter and J. Schmidhuber, Long short-term memory, Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997
16. F.A. Gers, N.N. Schraudolph, and J. Schmidhuber, Learning precise timing with LSTM recurrent networks, The Journal of Machine Learning Research, vol. 3, pp. 115-143, 2003
17. C.M. Bishop, Mixture density networks, Technical Report, Aston University, 1997
18. T. Tieleman and G. Hinton, Lecture 6.5-rmsprop, coursera: Neural networks for machine learning, 2012
19. M. Hermans and B. Schrauwen, Training and analysing deep recurrent neural networks, in Advances in Neural Information Processing Systems, 2013, pp. 190-198
20. A. Graves, Generating sequences with recurrent neural networks, arXiv preprint arXiv:1308.0850, 2013
21. A. Graves, http://sourceforge.net/projects/rnnl
22. K. Richmond, P. Hoole, and S. King, Announcing the electromagnetic articulography (day 1) subset of the mngu0 articulatory corpus, in Proc. INTERSPEECH, 2009, pp. 1505-1508
23. J.S. Perkell, M.H. Cohen, M.A. Svirsky, M.L. Matthies, I. Garabieta, and M.T. Jackson, Electromagnetic midsagittal articulometer systems for transducing speech articulatory movements, The Journal of the Acoustical Society of America, vol. 92, no. 6, pp. 3078-3096, 1992
24. H.W. Strube, Linear prediction on a warped frequency scale, The Journal of the Acoustical Society of America, vol. 68, no. 4, pp. 1071-1076, 1980
25. C. Qin, M.A. Carreira-Perpinán, and M. Farhadloo, Adaptation of a tongue shape model by local feature transformations, in Proc. INTERSPEECH, 2010, pp. 1596-1599