Production models as a structural basis for automatic speech recognition

Speech Communication

Volumn 22, Issue 2-3, 1997, Pages 93-111

  Deng, L ^a   Ramsay, G ^a   Sun, D ^b  

^a UNIVERSITY OF WATERLOO   (Canada)

^b LUCENT TECHNOLOGIES   (United States)

Author keywords

Analysis by synthesis; Articulatory dynamics; Articulatory features; Nonlinear phonology; Phonetic interface; Speech production; Speech recognition; Stochastic modeling; Stochastic target model

Indexed keywords

APPROXIMATION THEORY; MATHEMATICAL MODELS; PROBABILITY; RANDOM PROCESSES; SPEECH ANALYSIS; SPEECH SYNTHESIS; USER INTERFACES;

ARTICULATORY DYNAMICS; NONLINEAR PHONOLOGY; PHONETIC INTERFACES; STOCHASTIC TARGET MODELS;

SPEECH RECOGNITION;

EID: 0031198059     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(97)00018-6     Document Type: Article

References (82)

1. S. Anderson, Nasal consonants and the internal structure of segments, Language 52 (1976) 326-344.
2. G. Bailly, R. Laboissière, J.L. Schwartz, Formant trajectories as audible gestures: 1n alternative for speech synthesis, J. Phonetics 19 (1) (1991) 9-23.
3. G. Bailly, Recovering place of articulation for occlusives in VCV's. In: Proc. XIII-th ICPhS, 1995, Vol. 2, pp. 230-233.
4. R. Bakis, Coarticulation modeling with continuous-state HMMs. In: Proc. IEEE Workshop Automatic Speech Recognition, 1991. Harriman, New York, 1991, pp. 20-21.
5. R. Bakis, An articulatory-like speech production model with controlled use of prior knowledge. Notes from Frontiers in Speech Processing, CD-ROM, 1993.
6. L. Baum, An inequality and associated maximization technique in statistical estimation for probabilistic functions of Markov processes, Inequalities 3 (1972) 1-8.
7. N. Bitar, C. Espy-Wilson, Speech parameterization based on phonetic features: Application to speech recognition. In: Proc. Eurospeech, 1995, Vol. 2, pp. 1411-1414.
8. C. Blackburn, S. Young, Towards improved speech recognition using a speech production model. In: Proc. Eurospeech, 1995, Vol. 2, pp. 1623-1626.
9. L.-J. Boë, P. Perrier, G. Bailly, The geometric vocal tract variables controlled for vowel production: Proposals for constraining acoustic-to-articulatory inversion, J. Phonetics 20 (1992) 27-38.
10. H. Bourlard, H. Hermansky, N. Morgan, Towards increasing speech recognition error rates, Speech Communication 18 (3) (1996) 205-231.
11. C. Browman, L. Goldstein, Articulatory phonology: An overview, Phonetica 49 (1992) 155-180.
12. W. Chow, B.H. Juang, C.H. Lee, A minimum error rate pattern recognition approach to speech recognition, Internat. J. Pattern Recog. Artif. Intell. 8 (1996) 5-31.
13. W. Chow, B.H. Juang, C.H. Lee, Statistical and discriminative methods for speech recognition. In: C. Lee, F. Soong, K. Paliwal (Eds.), Automatic Speech and Speaker Recognition -Advanced Topics. Kluwer Academic Publishers, Boston, MA, 1996, pp. 109-132.
14. N. Clements, E. Hume, The internal organization of speech sounds. In: J. Goldsmith (Ed.), The Handbook of Phonological Theory. Blackwell, Cambridge, 1995, pp. 206-244.
15. J. Cohen, The summers of our discontent. In: Proc. Addendum ICSLP, 1996, pp. 9-10.
16. C. Coker, A model of articulatory dynamics and control, Proc. IEEE 64 (1976) 452-460.
17. L. Deng, Design of a feature-based speech recognizer aiming at integration of auditory processing, signal modeling, and phonological structure of speech. J. Acoust. Soc. Amer. 93 (4) Pt. 2 (1993) 2318.
18. L. Deng, A generalized hidden Markov model with state-conditioned trend functions of time for the speech signal, Signal Processing 27 (1) (1992) 65-78.
19. L. Deng, M. Aksmanovic, D. Sun, J. Wu, Speech recognition using hidden Markov models with polynomial regression functions as nonstationary states, IEEE Trans. Speech Audio Process. 2 (4) (1994) 507-520.
20. L. Deng, D. Braam, Context-dependent Markov model structured by locus equations: Application to phonetic classification, J. Acoust. Soc. Amer. 96 (1994) 2008-2025.
21. L. Deng, H. Sameti, Speech recognition using dynamically defined speech units, Proc. ICSLP 4 (1994) 2167-2170.
22. L. Deng, D. Sun, A statistical approach to automatic speech recognition using the atomic speech units constructed from overlapping articulatory features, J. Acoust. Soc. Amer. 95 (1994) 2702-2719.
23. L. Deng, J. Wu, H. Sameti, Improved speech modeling and recognition using multi-dimensional articulatory states as primitive speech units. In: Proc. ICASSP, Vol. 1, 1995, pp. 385-388.
24. L. Deng, H. Sameti, Transitional speech units and their representation by the regressive Markov states: Applications to speech recognition, IEEE Trans. Speech Audio Process. 4 (4) (1996) 301-306.
25. L. Deng, M. Lennig, P. Mermelstein, Modeling microsegments of stop consonants in a hidden Markov model based word recognizer, J. Acoust. Soc. Amer. 87 (1990) 2738-2747.
26. L. Deng, K. Erler, Structural design of a hidden Markov model based speech recognizer using multi-valued phonetic features: Comparison with segmental speech units, J. Acoust. Soc. Amer. 92 (1992) 3058-3067.
27. L. Deng, K. Hasanein, M. Elmasry, Analysis of correlation structure for a neural predictive model with application to speech recognition, Neural Networks 7 (2) (1994) 331-339.
28. L. Deng, C. Rathinavalu, A Markov model containing state-conditioned second-order nonstationarity: Application to speech recognition, Comput. Speech Language 9 (1) (1995) 63-86.
29. V. Digalakis, J. Rohlicek, M. Ostendorf, ML estimation of a stochastic linear system with the EM algorithm and its application to speech recognition, IEEE Trans. Speech Audio Process. 1 (1993) 431-442.
30. J. Durand, F. Katamba, Frontiers of Phonology: Atoms, Structures, Derivations. Longman, London, 1995.
31. E. Eide, A linguistic feature representation of the speech waveform. In: Proc. ICASSP, Vol. 2, 1993, pp. 483-486.
32. K. Erler, L. Deng, Hidden Markov model representation of quantized articulatory features for speech recognition, Comput. Speech Language 7 (3) (1993) 265-282.
33. E. Foster et al., Automatic learning of word pronunciation from data, In: Proc. Addendum ICSLP, 1996, pp. 28-29.
34. T. Fourakis, R. Port, Stop epenthesis in English, J. Phonetics 14 (1986) 197-221.
35. S. Furui, Flexible speech recognition. In: Proc. Eurospeech, Vol. 3, 1995, pp. 1595-1603.
36. O. Ghitza, M. Sondhi, Hidden Markov models with templates as nonstationary states: an application to speech recognition, Comput. Speech Language 7 (1993) 101-119.
37. J.A. Goldsmith, 1990. Autosegmental and Metrical Phonology. Blackwell, Oxford.
38. F.H. Guenther, A modeling framework for speech motor development and kinematic articulator control. In: Proc. XIII-th ICPhS, Vol. 2, 1995, pp. 92-99.
39. J. Hogden, A maximum likelihood approach to estimating speech articulator positions from speech acoustics. J. Acoust. Soc. Amer. 100 (4) Pt. 2 (1996) 2663-2664.
40. W. Holmes, M. Russell, Modeling speech variability with segmental HMMs. In: Proc. Eurospeech, 1996, Vol. 1, pp. 447-450.
41. M. Honda, T. Kaburagi, A dynamical articulatory model using potential task representation. In: Proc. ICSLP, 1995, Vol. 1, pp. 179-182.
42. R.A. Houde, A study of tongue body motion during selected speech sounds. SCRL, Santa Barbara, CA, 1968, SCRL Monogr. No. 2.
43. M. Hwang, X. Huang, F. Alleva, Predicting unseen triphones with senones. In: Proc. ICASSP, 1993, Vol. 1, pp. 311-315.
44. T. Kaburagi, M. Honda, A model of articulator trajectory formation based on the motor tasks of vocal-tract shapes, J. Acoust. Soc. Amer. 99 (5) (1996) 3154-3170.
45. P. Keating, The window model of coarticulation: articulatory evidence. In: J. Kingston, M. Beckman (Eds.), Papers in Laboratory Phonology, I. Cambridge University Press, Cambridge, 1990, pp. 451-470.
46. J. Kelso, E. Saltzman, B. Tuller, The dynamical perspectives on speech production: Data and theory, J. Phonetics 14 (1986) 29-59.
47. P. Kenny, M. Lennig, P. Mermelstein, Articulatory Markov models. In: Proc. IEEE Workshop Automatic Speech Recognition. Harriman, New York, 1991, pp. 22-23.
48. R. Kent et al., 1995. Models of speech production. In: N. Lass (Ed.), Principles of Experimental Phonetics. Mosby, London, pp. 3-45.
49. J. Keyser, K. Stevens, Feature geometry and the vocal tract, Phonology 11 (2) (1994) 207-236.
50. R. Laboissière, D.J. Ostry, P. Perrier, A model of human jaw and hyoid motion and its implications for speech production. In: Proc. XIII-th ICPhS, 1995, Vol. 2, pp. 60-67.
51. S. Levinson, L. Rabiner, M. Sondhi, An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition, Bell System Tech. J. 62 (1983) 1035-1074.
52. S. Liu, Landmark detection for distinctive feature-based speech recognition. Ph.D. Thesis, Massachusetts Institute of Technology, Cambridge, MA, 1995.
53. P. MacNeilage, Motor control of serial ordering in speech, Psychol. Rev. 77 (1970) 182-196.
54. S. Maeda, On articulatory and acoustic variabilities, J. Phonetics 19 (1991) 321-331.
55. J. Mahkoul, R. Schwartz, State of the art in continuous speech recognition, Proc. Nat. Acad. Sci. USA 92 (1995) 9956-9963.
56. R. McGowan, Recovering articulatory movement from formant frequency trajectories using task dynamics and a genetic algorithm: Preliminary model tests, Speech Communication 14 (1) (1994) 19-48.
57. R. McGowan, A. Faber, Speech production parameters for automatic speech recognition, J. Acoust. Soc. Amer. 101 (1) (1997) 28.
58. H. Meng, V. Zue, Signal representation comparison for phonetic classification. In: Proc. ICASSP, 1991, Vol. 1, pp. 285-288.
59. N. Morgan, H. Bourlard, Connectionist Speech Recognition - A Hybrid Approach. Kluwer, Boston, MA, 1994.
60. M. Ostendorf, From HMMs to segment models. In: C. Lee, F. Soong, K. Paliwal (Eds.), Automatic Speech and Speaker Recognition - Advanced Topics. Kluwer, Boston, MA, 1996, pp. 185-210.
61. J.S. Perkell, Phonetic features and the physiology of speech production. In: B. Butterworth (Ed.), Language Production. Academic Press, London, 1980.
62. J.S. Perkell, M.L. Matthies, M.A. Svirsky, M.I. Jordan, Goal-based speech motor control: A theoretical framework and some preliminary data, J. Phonetics 23 (1995) 23-35.
63. J.S. Perkell, Properties of the tongue help to define vowel categories: Hypotheses based on physiologically-oriented modeling, J. Phonetics 24 (1996) 3-22.
64. P. Perrier, D. Ostry, R. Laboissière, The equilibrium point hypothesis and its application to speech motor control, J. Speech Hearing Res. 39 (1996) 365-378.
65. L. Rabiner, B.H. Juang, C.H. Lee, An overview of automatic speech recognition. In: C. Lee, F. Soong, K. Paliwal (Eds.), Automatic Speech and Speaker Recognition - Advanced Topics. Kluwer, Boston, MA, 1996, pp. 1-30.
66. G. Ramsay, L. Deng, A stochastic framework for articulatory speech recognition. J. Acoust. Soc. Amer. 95 (5) Pt. 2 (1994) Abstract 2aSP19.
67. G. Ramsay, L. Deng, Articulatory synthesis using a stochastic target model of speech production. In: Proc. XIII-th ICPhS, 1995, Vol. 2, pp. 338-341.
68. G. Ramsay, L. Deng, Maximum likelihood estimation for articulatory speech recognition using a stochastic target model. In: Proc. Eurospeech, 1995, Vol. 2, pp. 1401-1404.
69. G. Ramsay, L. Deng, Optimal filtering and smoothing for speech recognition using a stochastic target model. In: Proc. ICSLP, 1996, Vol. 2, pp. 1113-1116.
70. M. Randolph, Speech analysis based on articulatory behavior. J. Acoust. Soc. Amer. 95 (5) Pt. 2 (1994) 1aSP15.
71. A. Robinson, F. Fallside, A recurrent error propagation network speech recognition system, Comput. Speech Language 5 (1991) 259-274.
72. R. Rose, J. Schroeter, M. Sondhi, The potential role of speech production models in automatic speech recognition, J. Acoust. Soc. Amer. 99 (3) (1996) 1699-1709.
73. P. Rubin, E. Saltzman, L. Goldstein, R. McGowan, M. Tiede, C. Browman, CASY and extensions to the task-dynamic model. In: Proc. 4th European Speech Production Workshop, Autrans, 1996, pp. 125-128.
74. E. Saltzman, K. Munhall, A dynamical approach to gestural patterning in speech production, Ecol. Psychol. 1 (1989) 333-382.
75. J. Schroeter, M.M. Sondhi, Techniques for estimating vocal-tract shapes from the speech signal, IEEE Trans. Speech Audio Process. 2 (1) (1994) 133-150.
76. H. Sheikhzadeh, L. Deng, Waveform-based speech recognition using hidden filter models: Parameter selection and sensitivity to power normalization, IEEE Trans. Speech Audio Process. 2 (1994) 80-91.
77. K. Shirai, M. Honda, Estimation of articulatory motion. In: Dynamic Aspects of Speech Production. University of Tokyo Press, Tokyo, 1976.
78. K. Stevens et al., Implementation of a model for lexical access based on features. In: Proc. ICSLP, 1992, Vol. 1, pp. 499-502.
79. K. Tokuda et al., An algorithm for speech parameter generation from continuous mixture HMMs with dynamic features. In: Proc. Eurospeech, 1995. Vol. 1, pp. 757-760.
80. A. Varga, R. Moore, HMM decomposition of speech and noise. In: Proc. ICASSP, 1990, pp. 845-848.
81. R. Wilhelms, Schätzung von artikulatorischen Bewegungen eines stylisierten Artikulatormodells aus dem Sprachsignal. Ph.D. Dissertation, Georg-August Universität, Göttingen, 1987.
82. S. Young, Large vocabulary continuous speech recognition: A review. In: Proc. IEEE Workshop on Automatic Speech Recognition, Snowbird, UT, 1995, pp. 3-28.