Retrieving tract variables from acoustics: A comparison of different machine learning strategies

IEEE Journal on Selected Topics in Signal Processing

Volumn 4, Issue 6, 2010, Pages 1027-1045

  Mitra, Vikramjit ^a   Nam, Hosung ^b   Espy Wilson, Carol Y ^a   Saltzman, Elliot ^b,c   Goldstein, Louis ^b,d  

^a UNIVERSITY OF MARYLAND   (United States)

^b HASKINS LABORATORIES   (United States)

^c BOSTON UNIVERSITY   (United States)

^d UNIVERSITY OF SOUTHERN CALIFORNIA   (United States)

Author keywords

Articulatory phonology; articulatory speech recognition (ASR); artificial neural networks (ANNs); coarticulation; distal supervised learning; mixture density networks; speech inversion; task dynamic and applications model; vocal tract variables

Indexed keywords

ARTICULATORY PHONOLOGY; ARTICULATORY SPEECH RECOGNITION (ASR); ARTIFICIAL NEURAL NETWORKS; CO-ARTICULATION; DISTAL SUPERVISED LEARNING; MIXTURE DENSITY NETWORKS; SPEECH INVERSION; TASK DYNAMIC AND APPLICATIONS MODEL; VOCAL-TRACTS;

FEEDFORWARD NEURAL NETWORKS; MIXTURES; SUPERVISED LEARNING;

SPEECH RECOGNITION;

EID: 78649390043     PISSN: 19324553     EISSN: None     Source Type: Journal    
DOI: 10.1109/JSTSP.2010.2076013     Document Type: Article

References (123)

1. B. S. Atal, J. J. Chang, M. V. Mathews, and J. W. Tukey, "Inversion of articulatory-to-acoustic transformation in the vocal tract by a computer sorting technique,"J. Acoust. Soc. Amer., vol. 63, pp. 1535-1555, 1978.
2. B. S. Atal, "Efficient coding of LPC parameters by temporal decomposition," in Proc. ICASSP, 1983, pp. 81-84.
3. C. Bishop, "Mixture density networks," Neural Computing Research Group, Dept., Comput. Sci., Aston Univ., Birmingham, U.K., Tech. Rep. NCRG/4288.
4. C. P. Browman and L. Goldstein, "Towards an articulatory phonology," Phonol. Yearbook, vol. 85, pp. 219-252, 1986.
5. C. P. Browman and L. Goldstein, "Some notes on syllable structure in articulatory phonology," Phonetica, vol. 45, pp. 140-155, 1988.
6. C. P. Browman and L. Goldstein, "Articulatory gestures as phonological units," Phonol., vol. 6, pp. 201-251, 1989.
7. C. P. Browman and L. Goldstein, "Gestural specification using dynamically-defined articulatory structures," J. Phonetics, vol. 18, no. 3, pp. 299-320, 1990.
8. C. P. Browman and L. Goldstein, "Representation and reality: Physical systems and phonological structure," J. Phonetics, vol. 18, pp. 411-424, 1990.
9. C. P.Browman and L. Goldstein, "Tiers in articulatory phonology, with some implications for casual speech," in Papers in Lab. Phon. I: Between the Grammar and the Physics of Speech, J. Kingston and M. E. Beckman, Eds. Cambridge, U.K.: Cambridge Univ. Press, 1991, pp. 341-376.
10. C. P. Browman and L. Goldstein, "Articulatory phonology: An overview," Phonetica, vol. 49, pp. 155-180, 1992.
11. D. Byrd and E. Saltzman, "The elastic phrase: Modeling the dynamics of boundary-adjacent lengthening," J. Phonetics, vol. 31, no. 2, pp. 149-180, 2003.
12. O. Cetin, A. Kantor, S. King, C. Bartels, M. Magimai-Doss, J. Frankel, and K. Livescu, "An articulatory feature-based tandem approach and factored observation modeling," in Proc. ICASSP, 2007, vol. 4, pp. 645-648.
13. S. Chang, M. Wester, and S. Greenberg, "An elitist approach to automatic articulatory-acoustic feature classification for phonetic characterization of spoken language," Speech Commun., vol. 47, no. 3, pp. 290-311, Nov. 2005.
14. S. Chen and A. Alwan, "Place of articulation cues for voiced and voiceless plosives and fricatives in syllable-initial position," in Proc. ICSLP, 2000, vol. 4, pp. 113-116.
15. N. Chomsky and M. Halle, The Sound Pattern of English. New York: Harper & Row, 1968.
16. J. Clark and C. Yallop, An introduction to Phonetics and Phonology, 2nd ed. Oxford, U.K.: Blackwell, 1995.
17. G. N. Clements and E. V. Hume, "The internal organization of speech sounds," in Handbook of Phonological Theory, J. A. Goldsmith, Ed. Cambridge, U.K.: Blackwell, 1995.
18. R. Cole, R. M. Stern, and M. J. Lasry, "Performing fine phonetic distinctions: Templates versus features," in Invariance and Variability of Speech Processes, J. S. Perkell and D. Klatt, Eds. Hillsdale, NJ: Lawrence Erlbaum Assoc., 1986, ch. 15, pp. 325-345.
19. R. Cole, M. Noel, T. Lander, and T. Durham, "New telephone speech corpora at CSLU," in Proc. 4th Euro. Conf. Speech Commun. Technol., 1995, vol. 1, pp. 821-824.
20. L. Deng and K. Erler, "Microstructural speech units and their HMM representations for discrete utterance speech recognition," in Proc. ICASSP, 1991, pp. 193-196.
21. L. Deng, "A generalized hidden Markov model with state-conditioned trend functions of time for the speech signal," Signal Process., vol. 27, no. 1, pp. 65-78, 1992.
22. L. Deng and D. Sun, "A statistical approach to ASR using atomic units constructed from overlapping articulatory features," J. Acoust. Soc. Amer., vol. 95, pp. 2702-2719, 1994.
23. L. Deng and D. Sun, "Phonetic classification and recognition using HMM representation of overlapping articulator features for all classes of English sounds," in Proc. ICASSP, 1994, pp. 45-47.
24. L. Deng, G. Ramsay, and D. Sun, "Production models as a structural basis for automatic speech recognition," Spec. Iss. Speech Prod. Modeling, Speech Commun., vol. 22, no. 2, pp. 93-112, 1997.
25. L. Deng, "A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition,"Speech Commun., vol. 24, no. 4, pp. 299-323, 1998.
26. L. Deng and J. Ma, "Spontaneous speech recognition using a statistical coarticulatory model for the hidden vocal-tract-resonance dynamics," J. Acoust. Soc. Amer., vol. 108, no. 6, pp. 3036-3048, 2000.
27. L. Deng, L. Lee, H. Attias, and A. Acero, "A structured speech model with continuous hidden dynamics and prediction-residual training for tracking vocal tract resonances," in Proc. ICASSP, 2004, pp. I557-I560.
28. L. Deng, D. Yu, and A. Acero, "Structured speech modeling," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 5, pp. 1492-1504, Sep. 2006.
29. O.Deshmukh, C. Espy-Wilson, A.Salomon, and J. Singh, "Use of temporal information: Detection of the periodicity and aperiodicity profile of speech," IEEE Trans. Speech Audio Process., vol. 13, no. 5, pp. 776-786, Sep. 2005.
30. S. Dusan, "Statistical estimation of articulatory trajectories from the speech signal using dynamical and phonological constraints," Ph.D., Univ. of Waterloo, Dept. of Elect. Comput. Eng., Waterloo, ON, Canada, 2000.
31. K. Elenius and G. Tacacs, "Phoneme recognition with an artificial neural network," in Proc. Eurospeech, 1991, pp. 121-124.
32. K. Elenius and M. Blomberg, "Comparing phoneme and feature based speech recognition using artificial neural networks," in Proc. ICSLP, 1992, pp. 1279-1282.
33. K. Erler and L. Deng, "Hidden Markov model representation of quantized articulatory features for speech recognition," Comput., Speech, Lang., vol. 7, pp. 265-282, 1993.
34. C. Y. Espy-Wilson and S. E. Boyce, "The relevance of F4 in distinguishing between different articulatory configurations of American English/r/," J. Acoust. Soc. Amer., vol. 105, no. 2, p. 1400, 1999.
35. C. Y. Espy-Wilson, S. E. Boyce, M. Jackson, S. Narayanan, and A. Alwan, "Acoustic modeling of American English/r/," J. Acoust. Soc. Amer., vol. 108, no. 1, pp. 343-356, 2000.
36. C. A. Fowler and E. Saltzman, "Coordination and coarticulation in speech production," Lang. Speech, vol. 36, pp. 171-195, 1993.
37. C. A. Fowler and L. Brancazio, "Coarticulation resistance of American English consonants and its effects on transconsonantal vowel-to-vowel coarticulation," Lang. Speech, vol. 43, pp. 1-42, 2000.
38. C. A. Fowler, "Speech production and perception," in Handbook of Psychology, A. Healy and R. Proctor, Eds. New York: Wiley, 2003, vol. 4, Experimental Psychology, pp. 237-266.
39. J. Frankel, K. Richmond, S. King, and P. Taylor, "An automatic speech recognition system using neural networks and linear dynamic models to recover and model articulatory traces," in Proc. ICSLP, 2000, vol. 4, pp. 254-257.
40. J. Frankel and S. King, "ASR\Articulatory speech recognition," in Proc. Eurospeech, Denmark, 2001, pp. 599-602.
41. J. Frankel, M. Wester, and S. King, "Articulatory feature recognition using dynamic Bayesian networks," in Proc. Int. Conf. Spoken Lang. Process., Korea, 2004, pp. 1202-1205.
42. J. Frankel and S. King, "A hybrid ANN/DBN approach to articula-tory feature recognition," in Proc. Eurospeech, Interspeech, 2005, pp. 3045-3048.
43. O. Fujimura, S. Kiritani, and H. Ishida, "Computer controlled radiography for observation of movements of articulatory and other human organs," Comput. Biol. Med., vol. 3, pp. 371-384, 1973.
44. O. Fujimura, "Relative invariance of articulatory movements: An iceberg model," in Invariance & Variability of Speech Processes, J. S. Perkell and D. Klatt, Eds. Mahwah, NJ: Lawrence Erlbaum Assoc., 1986, ch. 11, pp. 226-242.
45. H. M. Hanson, R. S. McGowan, K. N. Stevens, and R. E. Beaudoin, "Development of rules for controlling the HLsyn speech synthesizer," in Proc. ICASSP, 1999, vol. 1, pp. 85-88.
46. H. M. Hanson and K. N. Stevens, "A quasiarticulatory approach to controlling acoustic source parameters in a Klatt-type formant synthesizer using HLsyn," J. Acoust. Soc. Amer., vol. 112, no. 3, pp. 1158-1182, 2002.
47. J. Harris, English Sound Structure. Oxford, U.K.: Blackwell, 1994.
48. M. Hasegawa-Johnson, K. Livescu, P. Lal, and K. Saenko, "Audiovisual speech recognition with articulator positions as hidden variables," in Proc. ICPhS, Saarbrucken, Germany, 2007, pp. 297-302.
49. X. He and L. Deng, Discriminative Learning for Speech Processing, G. H. Juang, Ed. San Mateo, CA: Morgan & Claypool, 2008.
50. G. E. Hinton, S. Osindero, and Y. Teh, "A fast learning algorithm for deep belief nets," Neural Comput., vol. 18, pp. 1527-1554, 2006.
51. J. Hogden, A. Löfqvist, V. Gracco, I. Zlokarnik, P. Rubin, and E. Saltzman, "Accurate recovery of articulator positions from acoustics: New conclusions based on human data," J. Acoust. Soc. Amer., vol. 100, no. 3, pp. 1819-1834, 1996.
52. J. Hogden, D. Nix, and P. Valdez, "An articulatorily constrained, maximum likelihood approach to speech recognition," Los Alamos National Laboratory, Los Alamos, NM, 1998, Tech. Rep. LA-UR-96-3945.
53. J. Hogden, P. Rubin, E. McDermott, S. Katagiri, and L. Goldstein, "Inverting mappings from smooth paths through Rn to paths through Rm. A technique applied to recovering articulation from acoustics," Speech Commun., vol. 49, no. 5, pp. 361-383, 2007.
54. F. J. Huang, E. Cosatto, and H. P. Graf, "Triphone based unit selection for concatenative visual speech synthesis," in Proc. ICASSP, Orlando, FL, 2002, vol. 2, pp. 2037-2040.
55. M. I. Jordan and D. E. Rumelhart, "Forward models\Supervised learning with a distal teacher," Cogn. Sci., vol. 16, pp. 307-354, 1992.
56. A. Juneja, "Speech recognition based on phonetic features and acoustic landmarks," Ph.D. dissertation, Univ. of MD, College Park, 2004.
57. T. P. Jung, A. K. Krishnamurthy, S. C. Ahalt, M. E. Beckman, and S. H. Lee, "Deriving gestural scores from articulator-movement records using weighted temporal decomposition," IEEE Trans. Speech Audio Process., vol. 4, no. 1, pp. 2-18, 1996.
58. D. Jurafsky, W. Ward, Z. Jianping, K. Herold, Y. Xiuyang, and Z. Sen, "What kind of pronunciation variation is hard for triphones to model?," in Proc. ICASSP, 2001, vol. 1, pp. 577-580.
59. A. Katsamanis, G. Papandreou, and P. Maragos, "Face active appearance modeling and speech acoustic information to recover articulation," IEEE Trans. Audio, Speech, Lang. Process., vol. 17, no. 3, pp. 411-422, Mar. 2009.
60. S. King and P. Taylor, "Detection of phonological features in continuous speech using neural networks," Comput., Speech, Lang., vol. 14, no. 4, pp. 333-353, 2000.
61. S. King, C. Bartels, and J. Bilmes, "SVitchboard 1: Small vocabulary tasks from Switchboard 1," in Proc. Interspeech, 2005, pp. 3385-3388.
62. K. Kirchhoff, "Robust speech recognition using articulatory information," Ph.D. dissertation, Univ. of Bielefeld, Bielefeld, Germany, 1999.
63. K. Kirchhoff, G. A. Fink, and G. Sagerer, "Combining acoustic and articulatory feature information for robust speech recognition," Speech Commun., vol. 37, pp. 303-319, 2002.
64. T. Kobayashi, M. Yagyu, and K. Shirai, "Application of Neural networks to articulatory motion estimation," in Proc. ICASSP, 1985, pp. 1001-1104.
65. P. Ladefoged, R. Harshman, L. Goldstein, and L. Rice, "Generating vocal tract shapes from formant frequencies," J. Acoust. Soc. Amer., vol. 64, pp. 1027-1035, 1978.
66. J. Laver, Principles of Phonetics. Oxford, U.K.: Oxford Univ. Press., 1994.
67. B. Lochschmidt, "Acoustic-phonetic analysis based on an articulatory model," in Automatic Speech Analysis and Recognition, J. P. Hayton, Ed. Dordrecht, The Netherlands: D. Reidel, 1982, pp. 139-152.
68. 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, "Articula-tory feature-based methods for acoustic and audio-visual speech recognition: Summary from the 2006 JHU Summer Workshop," in Proc. ICASSP, 2007, vol. 4, pp. 621-624.
69. J. Ma and L. Deng, "A path-stack algorithm for optimizing dynamic regimes in a statistical hidden dynamic model of speech," Comput., Speech, Lang., vol. 14, pp. 101-104, 2000.
70. S. Y. Manuel and R. A. Krakow, "Universal and language particular aspects of vowel-to-vowel coarticulation," Haskins Lab. Star. Rep, Speech Res. SR-77/78, pp. 69-78, 1984.
71. S. Y. Manuel, "The role of contrast in limiting vowel-to-vowel coar-ticulation in different languages," J. Acoust. Soc. Amer., vol. 88, pp. 1286-1298, 1990.
72. K. Markov, J. Dang, and S. Nakamura, "Integration of articulatory and spectrum features based on the hybrid HMM/BN modeling framework," Speech Commun., vol. 48, pp. 161-175, 2006. (Pubitemid 43012029)
73. A. Martinet, "Phonetics and linguistic evolution," in Manual of Phon., B. Malmberg, Ed. Amsterdam, The Netherlands: North-Holland, 1957, pp. 252-272.
74. R. S. McGowan, "Recovering articulatory movement from formant frequency trajectories using task dynamics and a genetic algorithm: Preliminary model tests," Speech Commun., vol. 14, no. 1, pp. 19-48, 1994.
75. F. Metze and A. Waibel, "A flexible stream architecture for ASR using articulatory features," in Proc. ICSLP, 2002, pp. 2133-2136.
76. J. Ming and F. J. Smith, "Improved phone recognition using Bayesian Triphone Models," in Proc. ICASSP, 1998, pp. 409-412.
77. V. Mitra, I. Özbek, H. Nam, X. Zhou, and C. Espy-Wilson, "From acoustics to vocal tract time functions," in Proc. ICASSP, 2009, pp. 4497-4500.
78. V. Mitra, H. Nam, C. Espy-Wilson, E. Saltzman, and L. Goldstein, "Noise robustness of Tract variables and their application to speech recognition," in Proc. Interspeech, U.K., 2009, pp. 2759-2762.
79. V. Mitra, H. Nam, and C. Espy-Wilson, "A step in the realization of a speech recognition system based on gestural phonology and landmarks," in Proc. 157th Meeting ASA, Portland, 2009, vol. 125, J. Acoust. Soc. Amer., p. 2530.
80. V. Mitra, H. Nam,C.Espy-Wilson, E.Saltzman, and L. Goldstein, "Recovering speech gestures using a cascaded neural network," J. Acoust. Soc. Amer., submitted for publication.
81. A. Mohamed, G. Dahl, and G. Hinton, "Deep belief networks for phone recognition," in Proc. NIPS Workshop on Deep Learning for Speech Recognition and Related Applications, 2009.
82. M. F. Moller, "A scaled conjugate gradient algorithm for fast supervised learning," Neural Netw., vol. 6, pp. 525-533, 1993.
83. R. D. Mori, P. Laface, and E. Piccolo, "Automatic detection and description of syllabic features in continuous speech," IEEE Trans. Acoust., Speech Signal Process., vol. 24, no. 5, pp. 365-379, Oct. 1976.
84. H. Nam, L. Goldstein, E. Saltzman, and D. Byrd, "Tada: An enhanced, portable task dynamics model in Matlab," J. Acoust. Soc. Amer., vol. 115, no. 5-2, p. 2430, 2004.
85. D. Neiberg, G. Ananthakrishnan, and O. Engwall, "The acoustic to articulation mapping: Non-linear or Non-unique?," in Proc. Interspeech, 2008, pp. 1485-1488.
86. S. E. G. Ohman, "Coarticulation in VCV utterances: Spectrographic measurements," J. Acoust. Soc. Amer., vol. 39, pp. 151-168, 1966.
87. T. Okadome, S. Suzuki, and M. Honda, "Recovery of articulatory movements from acoustics with phonemic information," in Proc. 5th Seminar Speech Production, Bavaria, Germany, 2000, pp. 229-232.
88. M. K. Omar and M. Hasegawa-Johnson, "Maximum mutual information based acoustic features representation of phonological features for speech recognition," in Proc. ICASSP, 2002, vol. 1, pp. 81-84.
89. M. Ostendorf, "Moving beyond the 'beads-on-a-string' model of speech," in Proc. IEEE Auto. Speech Recog. Understanding Workshop, 1999, vol. 1, pp. 79-83.
90. G. Papcun, J. Hochberg, T. R. Thomas, F. Laroche, J. Zachs, and S. Levy, "Inferring articulation and recognizing gestures from acoustics with a neural network trained on X-ray microbeam data," J. Acoust. Soc. Amer., vol. 92, no. 2, pp. 688-700, 1992.
91. C. Qin and M. Á. Carreira-Perpiñán, "An empirical investigation of the nonuniqueness in the acoustic-to-articulatory mapping," in Proc. Interspeech, 2007, pp. 74-77.
92. M. G. Rahim, W. B. Kleijn, J. Schroeter, and C. C. Goodyear, "Acoustic-to-articulatory parameter mapping using an assembly of neural networks," in Proc. ICASSP, 1991, pp. 485-488.
93. M. G. Rahim, C. C. Goodyear, W. B. Kleijn, J. Schroeter, and M. Sondhi, "On the use of neural networks in articulatory speech synthesis," J. Acoust. Soc. Amer., vol. 93, no. 2, pp. 1109-1121, 1993.
94. D. Recasens, "Timing constraints and coarticulation: Alveolo-palatals and sequences of alveolar + [j] in Catalan," Phonetica, vol. 41, pp. 125-139, 1984.
95. K. Richmond, "Estimating articulatory parameters from the acoustic speech signal," Ph.D., Univ. of Edinburgh, Edinburgh, U.K., 2001.
96. K.Richmond, "Trajectory mixture density networks with multiple mixtures for acoustic-articulatory inversion," Lecture Notes in Comput. Sci., vol. 4885/2007, pp. 263-272, 2007.
97. J. Ryalls and S. J. Behrens, Introduction to Speech Science: From Basic Theories to Clinical Applications. Boston, MA: Allyn & Bacon, 2000.
98. E. Saltzman and K. Munhall, "A dynamical approach to gestural patterning in speech production," Ecol. Psychol., vol. 1, no. 4, pp. 332-382, 1989.
99. O. Schmidbauer, "Robust statistic modelling of systematic variabilities in continuous speech incorporating acoustic-articulatory relations," in Proc. ICASSP, 1989, pp. 616-619.
100. B. Schrauwen and L. Buesing, "A hierarchy of recurrent networks for speech recognition," in Proc. NIPS Workshop on Deep Learning for Speech Recognition and Related Applications, 2009.
101. K. Shirai and T. Kobayashi, "Estimating articulatory motion from speech wave," Speech Commun., vol. 5, pp. 159-170, 1986.
102. A. Smola and B. Scholkhopf, "A tutorial on support vector regression," Statist. Comput., vol. 14, no. 3, pp. 199-222, 2004.
103. K. N. Stevens, "Toward a model for speech recognition," J. Acoust. Soc. Amer., vol. 32, pp. 47-55, 1960.
104. K. N. Stevens, S. Manuel, and M. Matthies, "Revisiting place of articulation measures for stop consonants: Implications for models of consonant production," in Proc. Int. Cong. Phon. Sci., 1999, vol. 2, pp. 1117-1120.
105. K. N. Stevens, Acoustic Phonetics (Current Studies in Linguistics). Cambridge, MA: MIT Press, 2000.
106. K. N. Stevens, "Toward a model for lexical access based on acoustic landmarks and distinctive features," J. Acoust. Soc. Amer., vol. 111, no. 4, pp. 1872-1891, 2002.
107. J. Sun and L. Deng, "Annotation and use of speech production corpus for building language-universal speech recognizers," in Proc. 2nd Int. Symp. Chinese Spoken Lang. Processi. ISCSLP, Beijing, China, Oct. 2000, vol. 3, pp. 31-34.
108. J. Sun and L. Deng, "An overlapping-feature-based phonological model incorporating linguistic constraints: Applications to speech recognition," J. Acoust. Soc. Amer., vol. 111, no. 2, pp. 1086-1101, 2002.
109. T. Toda, A. W. Black, and K. Tokuda, "Voice conversion based on maximum likelihood estimation of speech parameter trajectory," IEEE Trans. Audio, Speech, Lang. Process., vol. 15, no. 8, pp. 2222-2235, Nov. 2007.
110. R. Togneri and L. Deng, "Joint state and parameter estimation for a target-directed nonlinear dynamic system model," IEEE Trans. Signal Process., vol. 51, no. 12, pp. 3061-3070, Dec. 2003.
111. K. Tokuda, T. Yoshimura, T. Masuko, T. Kobayashi, and T. Kitamura, "Speech parameter generation algorithms for HMM-based speech synthesis," in Proc. ICASSP, Jun. 2000, vol. 3, pp. 1315-1318.
112. A. Toutios and K. Margaritis, "A support vector approach to the acoustic-to-articulatory mapping," in Proc. Interspeech, 2005, pp. 3221-3224.
113. A. Toutios and K. Margaritis, "Learning articulation from cepstral coefficients," in Proc. SPECOM, 2005.
114. V. Vapnik, Statistical Learning Theory. New York: Wiley, 1998.
115. J. Westbury, X-Ray Microbeam Speech Production Database User's Handbook. Madison: Univ. of Wisconsin, 1994.
116. M. Wester, S. Greenberg, and S. Chang, "A dutch treatment of an elitist approach to articulatory-acoustic feature classification," in Proc. Eu-rospeech, 2001, pp. 1729-1732.
117. M. Wester, J. Frankel, and S. King, "Asynchronous articulatory feature recognition using dynamic Bayesian networks," in Proc. Inst. Electronics, Info, Commun. Engi. Beyond HMM Workshop, 2004, vol. 104, pp. 37-42, SP2004-81-95.
118. J. Weston, A. Gretton, and A. Elisseeff, SVM Practical Session-How to Get Good Results Without Cheating. Tuebingen, Germany: Machine Learning Summer School, 2003.
119. C. Windheuser, F. Bimbot, and P. Haffner, "A probabilistic framework for word recognition using phonetic features," in Proc. ICSLP, 1994, pp. 287-290.
120. A. Wrench, The MOCHA-TIMIT Articulatory Database 1999 [Online]. Available: http://www.cstr.ed.ac.uk/artic/mocha.html
121. J. Zachs and T. R. Thomas, "A new neural network for articula-tory speech recognition and its application to vowel identification," Comput., Speech, Lang., vol. 8, pp. 189-209, 1994.
122. X. Zhuang, H. Nam, M. Hasegawa-Johnson, L. Goldstein, and E. Saltzman, "The entropy of articulatory phonological code: Recognizing gestures from tract variables," in Proc. Interspeech, 2008, pp. 1489-1492.
123. X. Zhuang, H. Nam, M. Hasegawa-Johnson, L. Goldstein, and E. Saltzman, "Articulatory phonological code for word classification," in Proc. Interspeech, 2009, pp. 2763-2766