A hybrid syllable recognition system based on vowel spotting

Speech Communication

Volumn 38, Issue 3-4, 2002, Pages 427-440

  Sirigos, John ^a   Fakotakis, Nikos ^a   Kokkinakis, George ^a  

^a UNIVERSITY OF PATRAS   (Greece)

Author keywords

Speech processing; Speech recognition; Syllable recognition

Indexed keywords

DATABASE SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; NEURAL NETWORKS; PROBABILITY; SPEECH PROCESSING;

DISCRETE HIDDEN MARKOV MODELS (DHMM);

SPEECH RECOGNITION;

EID: 0036836836     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(02)00012-2     Document Type: Article

References (28)

1. Anquita D., Pampolini M., Parodi G., Zunino R. YPROP: another accelerating technique for the back propagation. ICANN, Amsterdam, The Netherlands. September 13-16 1993;500-503.
2. Bacchiani M., Ostendorf M. Using automatically-derived acoustic sub-word units in large vocabulary speech recognition. ICSLP, paper no. 586. 1998.
3. Bahl L., Brown P., de Souza P., Mercer R. Maximum mutual information estimation of hidden Markov model parameters for speech recognition. Proc. Internat. Conf. Acoust. Speech Signal Process. 1986;49-52.
4. Bourlard H.A., Morgan N. Connectionist Speech Recognition. 1994;Kluwer Academic, Boston, MA.
5. Breiman, L., 1994. Stacked Regressions. Technical report, University of California, Berkeley.
6. Fakotakis N., Tsopanoglou E., Kokkinakis G. A text-independent speaker recognition system based on vowel spotting. Speech Communication. 12(1):1993;57-68.
7. Fisher W., Zue V., Bernstein J., Pallet D. An acoustic-phonetic database. JASA Suppl. A. 81:1986;592-600.
8. Franco H., Cohen M., Morgan N., Rumelhart A., Victor A. Context-dependent connectionist probability estimation in a hybrid hidden model-neural net speech recognition system. Computer Speech and Language. 8:1994;211-222.
9. Fritsch J., Finke M., Waibel A. Context-dependent hybrid HME/HMM speech recognition using polyphone clustering decision trees. Proc. Internat. Conf. Acoust. Speech Signal Process., Munich, Germany. 1997;340-344.
10. Hansen L.K., Salamon P. Neural network ensembles. IEEE Trans. Pattern Anal. Machine Intell. 12(10):1990;993-1001.
11. Hermansky H. Perceptual linear predictive analysis for speech. J. Acoust. Soc. Amer. 1990;1738-1752.
12. Hu Z., Schalkwyk J., Barnard E., Cole R. Speech recognition using syllable-like units. Proc. ICSLP, Philadelphia. 1996;452-456.
13. Jankowski C., Kalyauswamy A., Basson S., Spitz J. NTIMIT: a phonetically balanced, continuous speech, telephone bandwidth speech database. Proc. Internat. Conf. Acoust. Speech Signal Process, New Mexico, USA. April 1990;198-202.
14. Jones R.J., Downey S., Mason J.S. Continuous speech recognition using syllables. European Conf. Speech Comm. Technol. Eurospeech. 1997;1171-1174.
15. Juang B., Rabiner L. Hidden Markov models for speech recognition. Technometrics. 33(3):1991;251-272.
16. Krogh A., Vedelsby J. Neural network ensembles, cross validation and active learning. Advances in Neural Information Processing Systems. Vol. 7:1995;231-238 The MIT Press.
17. Lippman R.P. Review of neural networks for speech recognition. Neural Comput. 1(1):1989;1-38.
18. Mak B. Combining ANNs to improve phone recognition. Proc. Internat. Conf. Acoust. Speech Signal Process. 1997;670-673.
19. Makhoul J., Schwartz R. State of the art in continuous speech recognition. Voice Communication Between Humans and Machines. 1994;165-198 National Academy Press, Washington DC.
20. Mirchandani G. On hidden nodes for neural nets. IEEE Trans. Circuits Systems. 36(5):1989;152-159.
21. Riis S.K., Krogh A. Hidden neural networks: a framework for HMM/NN hybrids. Proc. Internat. Conf. Acoust. Speech Signal Process. 1997;670-674.
22. Saul L., Jordan M. Boltzman chains and hidden Markov models. Advances in Neural Information Processing Systems 7. Morgan Kaufmann. 1995;435-442.
23. Schalkwyk J., Vermeulen P., Fanty M., Cole R. Embedded implementation of a hybrid neural-network telephone speech recognition system. Internat. Conf. Neural Networks Signal Process. 1995;800-803.
24. Sirigos J., Fakotakis N., Kokkinakis G. A comparison of several speech parameters for speaker independent speech recognition and speaker recognition. European Conf. Speech Comm. Technol., Eurospeech, Madrid, Spain. September 18-21 1995;1301-1304.
25. Sirigos J., Fakotakis N., Kokkinakis G. A high-performance vowel spotting system based on a multi-stage architecture. Eusipco'98, Rhodes, Greece. 1998;800-803.
26. Vogl T.P., Mangis J.K., Rigler A.K., Zink W.T., Alkon D.L. Accelerating the convergence of the back-propagation method. J. Biological Cybernet. 59:1990;257-263.
27. Yu H., Oh Y.H. A neural network using accoustic sub-word units for continuous speech recognition. ICSLP. October 1996;506-509.
28. Zavaliagkos G., Zhao Y., Schwartz R, Makhoul J. A hybrid segmental neural net/hidden Markov model system for continuous speech recognition. IEEE Trans. Speech Audio Process. Part II. 2(1):1994;151-160.