Articulatory features from deep neural networks and their role in speech recognition

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

Volumn , Issue , 2014, Pages 3017-3021

  Mitra, Vikramjit ^a   Sivaraman, Ganesh ^b   Nam, Hosung ^c   Espy Wilson, Carol ^b   Saltzman, Elliot ^c,d  

^a SRI INTERNATIONAL   (United States)

^b UNIVERSITY OF MARYLAND   (United States)

^c HASKINS LABORATORIES   (United States)

^d BOSTON UNIVERSITY   (United States)

Author keywords

articulatory trajectories; automatic speech recognition; deep neural networks; vocal tract variables

Indexed keywords

CONTINUOUS SPEECH RECOGNITION; SIGNAL PROCESSING; TRAJECTORIES;

ARTICULATORY FEATURES; ARTICULATORY INFORMATIONS; AUTOMATIC SPEECH RECOGNITION; BASE-LINE PERFORMANCE; DEEP NEURAL NETWORKS; SPEECH RECOGNITION PERFORMANCE; TRAJECTORY ESTIMATION; VOCAL-TRACTS;

SPEECH;

EID: 84905234271     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2014.6854154     Document Type: Conference Paper

References (30)

1. R. Daniloff and R. Hammarberg, "On defining coarticulation", J. of Phonetics, Vol.1, pp. 239-248, 1973.
2. K. N. Stevens, "Toward a model for speech recognition", J. of Acoust. Soc. Am., Vol.32, pp. 47-55, 1960.
3. K. Kirchhoff, Robust Speech Recognition Using Articulatory Information, PhD Thesis, University of Bielefeld, 1999.
4. J. Frankel and S. King, "ASR-Articulatory Speech Recognition", Proc. of Eurospeech, pp. 599-602, Denmark, 2001.
5. L. Deng and D. Sun, "A statistical approach to automatic speech recognition using atomic units constructed from overlapping articulatory features", J. of Acoust. Soc. Am., 95(5), pp. 2702-2719, 1994.
6. S. King, J. Frankel, K. Livescu, E. McDermott, K. Richmond and M. Wester, "Speech production knowledge in automatic speech recognition", J. Acoust. Soc. of Am., 121(2), pp. 723-742, 2007.
7. K. Livescu, O. Cetin, M. Hasegawa-Johnson, S. King, C. Bartels, N. Borges, A. Kantor, P. Lal, L. Yung, A. Bezman, S. Dawson-Haggerty, B. Woods, J. Frankel, M. Magimai-Doss and K. Saenko, "Articulatory feature-based methods for acoustic and audio-visual speech recognition: Summary from the 2006 JHU Summer Workshop", Proc. of ICASSP, Vol.4, pp.621-624, 2007.
8. M. Richardson, J. Bilmes and C. Diorio, "Hidden-articulator Markov models for speech recognition", Speech Comm., 41(2-3), pp. 511-529, 2003.
9. V. Mitra, H. Nam, C. Espy-Wilson, E. Saltzman and L. Goldstein, "Articulatory information for noise robust speech recognition", IEEE Trans. on Audio, Speech and Language Processing, Vol. 19, Iss. 7, pp. 1913-1924, 2010.
10. V. Mitra, H. Nam and C. Espy-Wilson, "Robust speech recognition using articulatory gestures in a Dynamic Bayesian Network framework", Proc. of Automatic Speech Recognition & Understanding Workshop, ASRU, pp. 131-136, Hawaii, 2011.
11. V. Mitra, W. Wang, A. Stolcke, H. Nam, C. Richey, J. Juan, and M. Liberman, "Articulatory features for large vocabulary speech recognition," in Proc. IEEE ICASSP, Vancouver, May 2013.
12. B. Uria, S. Renals, and K. Richmond, "A Deep Neural Network for Acoustic-Articulatory Speech Inversion", in NIPS 2011 Workshop on Deep Learning and Unsupervised Feature Learning, 2011.
13. Canevari, C., Badino, L., Fadiga, L., Metta, G., "Relevanceweighted reconstruction of articulatory features in Deep Neural Network-based Acoustic-to-Articulatory Mapping", in Proc. of Interspeech, 2013.
14. V. Mitra, H. Nam, C. Espy-Wilson, E. Saltzman, L. Goldstein, "Gesture-based Dynamic Bayesian Network for Noise robust Speech Recognition," in Proc. of ICASSP, pp. 5172-5175, 2011.
15. L. Deng and D. Sun, "A statistical approach to ASR using atomic units constructed from overlapping articulatory features", J. of Acoust. Soc. Am., 95, pp. 2702-2719, 1994.
16. K. Erler and L. Deng, "Hidden Markov model representation of quantized articulatory features for speech recognition", Comp., Speech & Lang., Vol. 7, pp. 265-282, 1993.
17. H. Nam, L. Goldstein, E. Saltzman and D. Byrd, "Tada: An enhanced, portable task dynamics model in Matlab", J. of Acoust. Soc. Am., 115(5), pp. 2430, 2004.
18. H. M. Hanson and K. N. Stevens, "A quasiarticulatory approach to controlling acoustic source parameters in a Klatt-type formant synthesizer using HLsyn", J. of Acoust. Soc. Am., 112(3), pp. 1158-1182, 2002.
19. C. P. Browman and L. Goldstein, "Towards an Articulatory Phonology", Phonology Yearbook, 85, pp. 219-252, 1986.
20. C. P. Browman and L. Goldstein, "Articulatory Phonology: An Overview", Phonetica, 49, pp. 155-180, 1992.
21. E. Saltzman and K. Munhall, "A Dynamical Approach to Gestural Patterning in Speech Production", Ecological Psychology, 1(4), pp. 332-382, 1989.
22. http://www.speech.cs.cmu.edu/cgi-bin/cmudict
23. G. Hirsch, "Experimental framework for the performance evaluation of speech recognition front-ends on a large vocabulary task", ETSI STQ-Aurora DSR Working Group, June 4, 2001.
24. H. Hermansky and N. Morgan, "RASTA processing of speech," IEEE Trans. Speech Audio Proc., vol.2, pp.578-589, 1994.
25. V. Mitra, H. Franco, M. Graciarena and A. Mandal, "Normalized amplitude modulation features for large vocabulary noise-robust speech recognition", Proc. IEEE CASSP, pp. 4117-4120, 2012.
26. V. Mitra, H. Franco, M. Graciarena, "Damped Oscillator Cepstral Coefficients for Robust Speech Recognition," Proc. Interspeech, pp. 886-890, 2013.
27. V. Mitra, H. Nam, C. Espy-Wilson, E. Saltzman and L. Goldstein, "Retrieving tract variables from acoustics: A comparison of different machine learning strategies", IEEE Journal of Selected Topics on Signal Processing, Sp. Iss. on Statistical Learning Methods for Speech and Language Processing, Vol. 4, Iss. 6, pp. 1027-1045, 2010.
28. K. Richmond, "Estimating Articulatory parameters from the Acoustic Speech Signal", PhD Thesis, Univ. of Edinburgh, UK, 2001.
29. A. Stolcke, B. Chen, H. Franco, V. R. R. Gadde, M. Graciarena, M.-Y. Hwang, K. Kirchhoff, A. Mandal, N. Morgan, X. Lin, T. Ng, M. Ostendorf, K. Sonmez, A. Venkataraman, D. Vergyri, W. Wang, J. Zheng and Q. Zhu, "Recent Innovations in Speech-to-Text Transcription at SRI-ICSI-UW", IEEE Trans. on Audio, Speech and Language Processing, 14(5), pp. 1729-1744, 2006.
30. A. Mandal, M. Ostendorf and Andreas Stolcke, "Improving robustness of MLLR adaptation with speaker-clustered regression class trees", Computer Speech & Language, 23, pp. 176 199 (2009). ISSN 0885-2308.