Incorporating linguistic theories of pronunciation variation into speech-recognition models

Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences

Volumn 358, Issue 1769, 2000, Pages 1325-1338

  Ostendorf, Mari ^a  

^a University of Washington   (United States)

Author keywords

Acoustic modelling; Phonetic variation; Pronunciation modelling

Indexed keywords

EID: 0347307067     PISSN: 1364503X     EISSN: None     Source Type: Journal    
DOI: 10.1098/rsta.2000.0589     Document Type: Article

References (42)

1. Bilmes, J. 1999 Natural statistical models for automatic speech recognition. PhD thesis, Department of EECS, University of California, Berkeley, USA.
2. Bitar, N. & Espy-Wilson, C. 1996 Knowledge-based parameters for HMM speech recognition. In Proc. Int. Conf. Acoustics, Speech and Signal Processing, pp. 29-32.
3. Breiman, L., Friedman, J., Olshen, R. & Stone, C. 1984 Classification and regression trees. Monterey, CA: Wadsworth and Brooks.
4. Clark, J. & Yallop, C. 1995 An introduction to phonetics and phonology. London: Blackwell.
5. Clements, G. 1985 The geometry of phonological features. In Phonology Yearbook, vol. 2, pp. 223-252.
6. Cohen, M. 1989 Phonological structures for speech recognition. PhD thesis, University of California, Berkeley, USA.
7. Deng, L. 1998 Computational models for speech production. In Computational models of speech pattern processing (ed. K. Ponting). Springer.
8. Deng, L. & Erler, K. 1992 Structural design of HMM speech recognizer using multi-valued phonetic features: comparison with segmental speech units. J. Acoust. Soc. Am. 92, 3058-3067.
9. Deng, L. & Wu, J. 1996 Hierarchical partition of the articulatory state space for overlapping-feature based speech recognition. In Proc. Int. Conf. Spoken Language Processing, pp. 2266-2269.
10. Dilley, L., Shattuck-Hufnagel, S. & Ostendorf, M. 1996 Glottalization of vowel-initial syllables as a function of prosodic structure. J. Phonetics 24, 423-444.
11. Donovan, R. 1996 Trainable speech synthesis. PhD thesis, University of Cambridge, UK.
12. Edwards, J. & Beckman, M. 1988 Articulatory timing and the prosodic interpretation of syllable duration. Phonetica 45, 156-174.
13. Eide, E. 1999 Automatic modeling of pronunciation variations. In Proc. DARPA Broadcast News Workshop, pp. 95-98.
14. Erler, K. & Deng, L. 1993 Hidden Markov model representation of quantized articulatory features for speech recognition. Comp. Speech Language 7, 265-282.
15. Finke, M. & Waibel, A. 1997 Speaking mode dependent pronunciation modeling in large vocabulary conversational speech recognition. In Proc. Eur. Conf. Speech Communication and Technology, pp. 2379-2382.
16. Fosler-Lussier, E., Greenberg, S. & Morgan, N. 1999 Incorporating contextual phonetics into automatic speech recognition. In Proc. Int. Congr. Phonetic Sciences, pp. 611-614.
17. Fougeron, C. & Keating, P. 1997 Demarcating prosodic groups with articulation. J. Acoust. Soc. Am. 97, 3384.
18. Greenberg, S. 1998 Speaking in shorthand - a syllable-centric perspective for understanding pronunciation variation. In Proc. ESCA Workshop on Modelling Pronunciation Variation for Automatic Speech Recognition, pp. 47-56.
19. Halle, M. 1992 Phonological features. In International encyclopedia of linguistics (ed. W. Bright). Oxford University Press.
20. Hübener, K. & Carson-Berndsen, J. 1994 Phoneme recognition using acoustic events. In Proc. Int. Conf. Spoken Language Processing, pp. 1919-1922.
21. Jordan, M., Ghahramani, Z. & Saul, L. 1996 Hidden Markov decision trees. MIT Computational Cognitive Science technical report 9606.
22. Keyser, S. & Stevens, K. 1994 Feature geometry and the vocal tract. Phonology 11, 207-236.
23. King, S., Stephenson, T., Isard, S., Taylor, P. & Strachan, A. 1998 Speech recognition via phonetically featured syllables. In Proc. Int. Conf. Spoken Language Processing, pp. 1031-1034.
24. Kirchhoff, K. 1996 Syllable-level desynchronisation of phonetic features for speech recognition. In Proc. Int. Conf. Spoken Language Processing, pp. 2274-2276.
25. Kirchhoff, K. 1998 Combining articulatory and acoustic information for speech recognition in noisy and reverberant environments. In Proc. Int. Conf. Spoken Language Processing, pp. 891-894.
26. Lahiri, A. 1999 Speech recognition with phonological features. In Proc. Int. Congr. Phonetic Sciences, pp. 715-718.
27. Lindblom, B. 1990 Explaining phonetic variation: a sketch of the H&H theory. In Speech production and speech modelling (ed. W. Hardcastle & A. Marchal), pp. 403-439. Dordrecht: Kluwer.
28. McAllister, D., Gillick, L. Scattone, F. & Newman, M. 1998 Fabricating conversational speech data with acoustic models: a program to examine model-data mismatch. In Proc. Int. Conf. Spoken Language Processing, pp. 1847-1850.
29. Niyogi, P., Mitra, P. & Sondhi, M. M. 1998 A detection framework for locating phonetic events. In Proc. Int. Conf. Spoken Language Processing, pp. 1067-1070.
30. Ostendorf, M. & Singer, H. 1997 HMM topology design using maximum likelihood successive state splitting. Comp. Speech Language 11, 17-42.
31. Ostendorf, M. (and 12 others) 1997 Modeling systematic variations in pronunciation via a language-dependent hidden speaking mode. Available from http://www.clsp.jhu.edu/ws96/.
32. Pallett, D., Fiscuss, J., Garofolo, J., Martin, A. & Przybocki, M. 1999 1998 Broadcast News benchmark test results: English and non-English word error rate performance measures. In Proc. DARPA Broadcast News Workshop, pp. 5-12.
33. Paul, D. 1997 Extensions to phone-state decision-tree clustering: single tree and tagged clustering. In Proc. Int. Conf. Acoustics, Speech and Signal Processing, pp. 1487-1490.
34. Riley, M. (and 10 others) 1999 Stochastic pronunciation modelling from hand-labelled phonetic corpora. Speech Commun. 29, 209-224.
35. Saraclar, M., Nock, H. & Khudanpur, S. 1999 Pronunciation modeling by sharing Gaussian densities across phonetic models. In Proc. Eur. Conf. Speech Communication and Technology, pp. 515-518.
36. Shattuck-Hufnagel, S. & Turk, A. 1996 A prosody tutorial for investigators of auditory sentence processing. J. Psycholing. Res. 25, 193-247.
37. Stevens, K. 1995 Applying phonetic knowledge to lexical access. In Proc. Eur. Conf. Speech Communication and Technology, pp. 3-11.
38. Stevens, K. & Keyser, S. 1989 Primary features and their enhancement in consonants. Language 65, 81-106.
39. Tajchman, G., Fosler, E. & Jurafsky, D. 1995 Building multiple pronunciation models for novel words using exploratory computational phonology. In Proc. Eur. Conf. Speech Communication and Technology, pp. 2247-2250.
40. Van Santen, J. 1997 Segmental duration and speech timing. In Computing prosody (ed. Y. Sagisaka, N. Campbell & N. Higuchi). Springer.
41. Weintraub, M., Fosler, E., Galles, C., Kao, Y.-H., Khudanpur, S., Saraclar, M. & Wegmann, S. 1996 WS96 project report: automatic learning of word pronunciation from data. Available from http://www.clsp.jhu.edu/ws96/.
42. Young, S., Odell, J. & Woodland, P. 1994 Tree-based state tying for high accuracy acoustic modelling. In Proc. Int. Conf. Acoustics, Speech and Signal Processing, pp. 307-312.