A multiple-level linear/linear segmental HMM with a formant-based intermediate layer

Computer Speech and Language

Volumn 19, Issue 2, 2005, Pages 205-225

  Russell, Martin J ^a   Jackson, Philip J B ^b  

^a UNIVERSITY OF BIRMINGHAM   (United Kingdom)

^b UNIVERSITY OF SURREY   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

MAPPING; MARKOV PROCESSES; MATHEMATICAL MODELS; PATTERN RECOGNITION; SPEECH ANALYSIS; SPEECH SYNTHESIS;

ACOUSTIC SPACES; ARTICULATORY-TO-ACOUSTIC MAPPING; HIDDEN MARKOV MODEL (HMM); PARAMETERISATION;

ACOUSTIC SIGNAL PROCESSING;

EID: 10844250035     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.csl.2004.08.001     Document Type: Article

References (35)

1. Bishop, C.M., 1995. Neural Networks for Pattern Recognition. Oxford University Press, Oxford, UK.
2. Bridle, J.S., Brown, M.D., Chamberlain, R.M., 1983. Continuous connected word recognition using whole-word templates. Radio Engineer 53, 167-177.
3. Deng, L., 1998. A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition. Speech Commun. 24 (4), 299-323.
4. Deng, L., Braam, D., 1994. Context-dependent markov model structured by locus equations: applications to phonetic classification. J. Acoust. Soc. Am. 96 (4), 2008-2025.
5. Deng, L., Ma, J., 2000. Spontaneous speech recognition using a statistical coarticulatory model for the vocal-tract-resonance dynamics. J. Acoust. Soc. Am. 108 (6), 3036-3048.
6. Digalakis, V., 1992. Segment-based stochastic models of spectral dynamics for continuous speech recognition. Ph.D. Thesis, Boston University, MA.
7. Frankel, J., Richmond, K., King, S., Taylor, P., 2000. An automatic speech recognition system using neural networks and linear dynamic models to recover the model articulatory traces. In: Proceedings of the International Conference on Spoken Language Proc., Beijing.
8. Gales, M.J.F., Young, S.J., 1993. Segmental hidden markov models. In: Proceedings of Eurospeech'93, Berlin, Germany, pp. 1579-1582.
9. Gao, Y., Bakis, R., Huang, J., Zhang, B., 2000. Multistage coarticulation model combining articulatory, formant and cepstral features. In: Proceedings of the International Conference on Spoken Language Proc., Beijing, vol. 1, pp. 25-28.
10. Garner, P.N. Holmes, W.J., 1998. On the robust incorporation of formant features into hidden Markov models for automatic speech recognition. In: Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing, Seattle, WA.
11. Garofolo, J.S., et al., 1993. TIMIT Acoustic-Phonetic Continuous Speech Corpus. Linguistic Data Consortium, University of Pennsylvania, Philadelphia, PA.
12. Ghitza, O., Sondhi, M., 1993. Hidden markov models with templates as non-stationary states: an application to speech recognition. Comput. Speech Lang. 2, 101-119.
13. Glass, J., 2003. A probabilistic framework for segment-based speech recognition. Comput. Speech Lang. 17 (2-3), 137-152.
14. Halberstadt, A., Glass, J., 1998. Heterogeneous measurements and multiple classifiers for speech recognition. In: Proceedings of the Intertnational Conference on Spoken Language Proc., Sydney, Australia, pp. 995-998.
15. Holmes, J.N., 2001. Speech processing system using formant analysis. US Patent US6292775.
16. Holmes, J.N., Garner, P.N., 2000. Using formant frequencies in speech recognition. In: Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing, Istanbul, Turkey, vol. 3, pp. 1347-1350.
17. Holmes, J., Holmes, W., 2001. Speech Synthesis and Recognition, second ed. Taylor & Francis, London and New York.
18. Holmes, W.J., Russell, M.J., 1999. Probablistic-trajectory segmental HMMs. Comput. Speech Lang. 13 (1), 3-37.
19. Holmes, J.N., Holmes, W.J., Garner, P.N., 1997. Using formant frequencies in speech recognition. In: Proceedings of Eurospeech'97, Rhodes, Greece, pp. 2083-2086.
20. Holmes, J.N., Mattingly, I.G., Shearme, J.N., 1964. Speech synthesis by rule. Lang. Speech 7, 127-143.
21. Hunt, M.J., 1987. Delayed decision making in speech recognition the case of formants. Pattern Recognition Lett. 6, 121-137.
22. Jackson, P.J.B., 2003. Improvements in classification accuracy through modelling duration. In: Proceedings of the ICPhS, Barcelona.
23. Jackson, P.J.B., Russell, M.J., 2002. Models of speech dynamics in a segmental-HMM recogniser using intermediate linear representations. In: Proceedings of the International Conference on Spoken Language Proc., Denver, CO, pp. 1253-1256.
24. Jackson, P.J.B., Lo, B.-H., Russell, M.J., 2002. Data-driven, nonlinear, formant-to-acoustic mapping for ASR. Electron. Lett. 38 (13), 667-669.
25. Lamel, L.F., Gauvain, J.L. (1993). High performance speaker-independent phone recognition using cdhmm. In: Proceedings of Eurospeech'93, Berlin, Germany, pp. 121-124.
26. Lo, B.H., Russell, M.J., 2003. Speech recognition using an intermediate articulatory layer and non-linear articulatory-to-acoustie mapping. One day meeting for young speech researchers. University College, London.
27. NIST 2000. Benchmark tests: Significance Tests for ASR. National Institute of Standards and Technology (Speech Group), Gaithersburg, MD. Available from: 〈http://www.nist.gov/speech/tests/sigtests/sigtests. htm〉.
28. Ostendorf, M., Digalakis, V.V., Kimball, O.A., 1996. From HMM's to segmental models: a unified view of stochastic modeling for speech recognition. IEEE Trans. Speech. Audio Process. 4 (5), 360-378.
29. Richards, H.B., Bridle, J.S., 1999. The HDM: a segmental Hidden Dynamic Model of coarticulation. In: Proceedings of the IEEE-ICASSP, Phoenix, AZ, pp. 357-360.
30. Russell, M.J., 1993. A segmental HMM for speech pattern modelling. In: Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing, Minneapolis, MN, pp. 499-502.
31. Russell, M.J., Jackson, P.J.B., Wong, L.P., 2003. Development of articulatory-based multi-level segmental HMMs for phonetic classification in ASR. In: Proceedings of the EC-VIP-MC03, Zagreb, Croatia.
32. Wiewiorka, A., Brookes, D.M., 1996. Exponential interpolation of states in a hidden Markov model. Proc. Inst. Acoust. 18 (9), 201-208.
33. Wilkinson, N., Russell, M.J., 2002. Improved phone recognition on TIMIT using formant frequency data and confidence measures. In: Proceedings of the International Conference on Spoken Language Proc., Denver, CO, pp. 2121-2124.
34. Young, S.J., Odell, J., Ollason, D., Valtchev, V., Woodland, P., 1997. The HTK Book, v2.1. Entropic Camb. Res. Lab., Cambridge, UK.
35. Zhou, J., Seide, F., Deng, L., 2003. Coarticulation modeling by embedding a target-directed hidden trajectory model into hmm-modeling and training. In: Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing, Hong Kong, vol. 1, pp. 744-747.