Deep-level acoustic-to-articulatory mapping for DBN-HMM based phone recognition

2012 IEEE Workshop on Spoken Language Technology, SLT 2012 - Proceedings

Volumn , Issue , 2012, Pages 370-375

  Badino, Leonardo ^a   Canevari, Claudia ^a   Fadiga, Luciano ^a   Metta, Giorgio ^a  

^a ISTITUTO ITALIANO DI TECNOLOGIA   (Italy)

Author keywords

Acoustic to articulatory mapping; deep belief networks; phone recognition

Indexed keywords

ACOUSTIC-TO-ARTICULATORY MAPPING; ARTICULATORY DATA; ARTICULATORY FEATURES; DEEP BELIEF NETWORKS; ERROR REDUCTION; MULTI-LAYER PERCEPTRONS; MULTI-LAYERED; PHONE RECOGNITION; PRE-TRAINING; SPEECH ACOUSTICS;

PATTERN RECOGNITION SYSTEMS; RECOVERY; SPEECH PROCESSING; TELEPHONE SETS; UNSUPERVISED LEARNING;

SPEECH RECOGNITION;

EID: 84874241818     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/SLT.2012.6424252     Document Type: Conference Paper

References (22)

1. Browman, C.P. and Goldstein, L., "Articulatory phonology: an overview", Phonetica 49 (34): 155-180, 1992.
2. D'Ausilio, A., Pulvermller, F., Salmas, P., Bufalari, I., Begliomini, C., and Fadiga, L., "The motor somatotopy of speech perception", Current Biology, 19, 381-385, 2009.
3. Erhan, D., Bengio, Y., Courville, A., Manzagol, P.A., Vincent, P., and Bengio, S., "Why Does Unsupervised Pre-training Help Deep Learning?", in J. of Machine Learning Research, 11 (625-660), 2011
4. Available at http://gp-you.org/.
5. Hinton, G.E., "Training products of experts by minimizing contrastive divergence", Neural Computation,vol. 14, pp. 1771-1800, 2002.
6. Hinton, G.E., Osindero, S. and Teh, Y., "A fast learning algorithm for deep belief nets", Neural Computation, vol. 18, pp. 1527-1554, 2006.
7. Hinton, G. E., and Salakhutdinov, R. R., "Reducing the dimensionality of data with neural networks", Science, Vol. 313. no. 5786, pp. 504-507, 28 July 2006.
8. Available at http://htk.eng.cam.ac.uk/.
9. King, S., Frankel, J., Livescu, K., McDermott, E., Richmond, K., and Wester, M.,"Speech production knowledge in automatic speech recognition", J. of the Acoust. Soc. Am., vol. 121(2), pp. 723-742, 2007.
10. Lindblom, B., Lubker, J., and Gay, T.,"Formant frequencies of some fixed-mandible vowels and a model of speech motor programming by predictive simulation", J. of Phonetics, vol. 7, 146-161, 1979.
11. Markov, K., Dang, J. and Nakamura, S., "Integration of articulatory and spectrum features based on the hybrid HMM/BN modeling framework" Speech Communication, 48, 161-175, 2006.
12. Mitra, V., Nam, H., Espy-Wilson, C., Saltzman, E., Goldstein, L., "Retrieving tract variables from acoustics: a comparison of different machine learning strategies", IEEE J. of Selected Topics in Signal Processing, vol. 4 (6), 1027-1045, 2010.
13. Mitra, V., Nam, H., Espy-Wilson, C., Saltzman, E., Goldstein, L., "Recognizing articulatory gestures from speech for robust speech recognition", J. Acoust. Soc. Am. 131 (3), 2270-2287, 2012
14. Mohamed, A. R., Dahl, G. E. and Hinton, G. E."Deep belief networks for phone recognition", NIPS 22, workshop on deep learning for speech recognition, 2010.
15. Ngiam, J., Nam, M., Lee, J., Khosla, H., Kim, A., and Ng, A.Y., "Multimodal deep learning", in ICML, 2011.
16. Qin, C., and Carreira-Perpinan, M.A. "An Empirical Investigation of the Nonuniqueness in the Acoustic-to-Articulatory Mapping", Proc. Interspeech, 2007
17. Richmond, K., King, S., and Taylor, P., "Modelling the uncertainty in recovering articulation from acoustics", Computer Speech and Language, vol. 17(2), pp. 153-172, 2003.
18. Roweiss, S., "Data driven production models for speech processing", PhD thesis, California Institute of Technology, Pasadena, California, 1999.
19. Toda, T., Black, A., and Tokuda, K., "Statistical Mapping between Articulatory Movements and Acoustic Spectrum Using a Gaussian Mixture Model", Speech Communication, vol. 50(3), 215-222, 2007.
20. Uria, B., Renals, S., and Richmond, K.,"A deep neural network for acoustic-articulatory speech inversion", In Proc. NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2011.
21. Wrench, A.A. and Richmond, K.,"Continuous speech recognition using articulatory data", in Proceedings of the International Conference on Spoken Language Processing, pp. 145-148, 2000.
22. Zlokarnik, I., "Adding articulatory features to acoustic features for automatic speech recognition". J. of the Acoust. Soc. Am., vol. 97(2), pp. 3246, 1995.