A segment-based interpretation of HMM/ANN hybrids

Computer Speech and Language

Volumn 21, Issue 3, 2007, Pages 562-578

  Tóth, László ^a   Kocsor, András ^a  

^a UNIVERSITY OF SZEGED   (Hungary)

Author keywords

[No Author keywords available]

Indexed keywords

HIDDEN MARKOV MODELS; NEURAL NETWORKS; PROBABILITY; SPEECH ANALYSIS;

PHONETIC DECODING; PROBABILITY FACTOR; SEGMENT CLASSIFICATION;

SPEECH RECOGNITION;

EID: 33847686469     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2006.12.001     Document Type: Article

References (29)

1. Austin, S., Zavaliagkos, G., Makhoul, J., Schwartz, R., 1992. Speech recognition using segmental neural nets. In: Proceedings of ICASSP'92, vol. 1, pp. 625-628.
2. Bourlard, H., Konig, Y., Morgan, N., 1994. REMAP: recursive estimation and maximization of a posteriori probabilities - application to transition-based connectionist speech recognition. ICSI Technical Report TR-94-064.
3. Bourlard H., Hermansky H., and Morgan N. Towards increasing speech recognition error rates. Speech Communication 18 (1996) 205-231
4. Chan Y.-C., and Siu M. Efficient computation of the frame-based extended union model and its application in speech recognition against partial temporal corruptions. Computer Speech and Language 19 (2005) 301-319
5. Clarkson, P., Moreno, P.J., 1999. On the Use of Support Vector Machines for Phonetic Classification. In: Proceedings of ICASSP'99, pp. 585-588.
6. Domingos P., and Pazzani M. On the optimality of the simple Bayesian classifier under zero-one loss. Machine Learning 29 (1997) 103-130
7. Gales, M.J.F., Young, S.J., 1993. The Theory of Segmental Hidden Markov Models. Technical Report CUED/F-INFENG/TR133, Cambridge University Engineering Department.
8. Glass, J.R., 1996. A probabilistic framework for feature-based speech recognition. In: Proceedings of ICSLP'96, pp. 2277-2280.
9. Greenberg, S., Chang S., 2000. Linguistic dissection of switchboard-corpus automatic speech recognition systems. In: Proceedings of ISCA Workshop on ASR: Challenges for the New Millenium, pp. 195-202.
10. Hagen A., and Morris A. Recent advances in the multi-stream HMM/ANN hybrid approach to noise robust ASR. Computer Speech and Language 19 (2005) 3-30
11. Hennebert, J., Ris, C., Bourlard, H., Renals, S., Morgan, N., 1997. Estimation of global posteriors and forward-backward training of hybrid HMM/ANN systems. In: Proceedings of Eurospeech'97, pp. 1951-1954.
12. Huang X., Acero A., and Hon H.-W. Spoken Language Processing (2001), Prentice Hall, New Jersey, USA
13. Jelinek F. Five speculations (and a divertimento) on the themes of H. Bourlard, H. Hermansky, and N. Morgan. Speech Communication 18 (1996) 242-246
14. Lee, S.C., Glass, J.R., 1998. Real-time probabilistic segmentation for segment-based speech recognition. In: Proceedings of ICSLP'98, pp.1803-1806.
15. Lee K.-F., and Hon H.-W. Speaker-independent phone recognition using hidden Markov models. IEEE Transactions on Acoustics, Speech and Signal Processing 37 11 (1989) 1641-1648
16. Leung, H.C., Hetherington, I.L., Zue, V.W., 1992. Speech recognition using stochastic segment neural networks. In: Proceedings of ICASSP'92, vol. 1, pp. 613-616.
17. Ming J., and Smith F.J. Union: A model for partial temporal corruption of speech. Computer Speech and Language 15 (2001) 217-231
18. Morgan, N., Bourlard, H., 1995. An Introduction to Hybrid HMM/Connectionist Continuous Speech Recognition. Signal Processing Magazine, May, 25-42.
19. Morris, A. C., Payne, S., Bourlard, H., 2002. Low cost duration modeling for noise robust speech recognition. In: Proceedings of ICSLP 2002, pp. 1025-1028.
20. Ostendorf M., Digalakis V., and Kimball O.A. From HMMs to segment models: a unified view of stochastic modeling for speech recognition. IEEE Transactions on Speech and Audio Processing 4 5 (1996) 1063-6676
21. Rabiner L., and Juang B.-H. Fundamentals of Speech Recognition (1993), Prentice Hall, New Jersey, USA
22. Saraçlar M., Nock H., and Khudanpur S. Pronunciation modeling by sharing Gaussian densities across phonetic models. Computer Speech and Language 14 (2000) 137-160
23. Tax D.M.J., van Breukelen M., Duin R.P.W., and Kittler J. Combining multiple classifiers by averaging or by multiplying?. Pattern Recognition 33 (2000) 1475-1485
24. Tóth, L., Kocsor, A., 2005. Explicit duration modelling in HMM/ANN Hybrids. Proceedings of TSD'2005, pp. 310-317.
25. Tóth L., Kocsor A., and Gosztolya G. Telephone speech recognition via the combination of knowledge sources in a segmental speech model. Acta Cybernetica 16 (2004) 643-657
26. Verhasselt J., Illina I., Martens J.-P., Gong Y., and Haton J.-P. Assessing the importance of the segmentation probability in segment-based speech recognition. Speech Communication 24 1 (1998) 51-72
27. Vicsi, K., Tóth, L., Kocsor, A., Csirik, J., 2002. MTBA - A Hungarian Telephone Speech Database. Híradástechnika, LVII (8) (in Hungarian). http://alpha.ttt.bme.hu/speech/hdbMTBA.php.
28. Young, S. et al., 1995. The HMM Toolkit (HTK) - software and manual. http://htk.eng.cam.ac.uk.
29. Zavaliagkos, G., Zhao, J., Schwartz, R., Makhoul, J., 1994. A Hybrid Segmental Neural Net/Hidden Markov Model System for Continuous Speech Recognition. IEEE Trans. Speech and Audio Proc., 2(1), Part II, pp. 151-159.