A new parameter smoothing method in the hybrid TDNN/HMM architecture for speech recognition

Speech Communication

Volumn 19, Issue 4, 1996, Pages 317-324

  Jang, C S ^a   Un, C K ^b  

^a Kumoh National Institute of Technology   (South Korea)

^b Korea Advanced Institute of Science and Technology (KAIST)   (South Korea)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COMPUTER ARCHITECTURE; COMPUTER SIMULATION; ERRORS; FUZZY SETS; HYBRID COMPUTERS; MARKOV PROCESSES; MATHEMATICAL MODELS; MATRIX ALGEBRA; NEURAL NETWORKS; PROBABILITY; VECTOR QUANTIZATION;

FUZZY VECTOR QUANTIZER; HIDDEN MARKOV MODEL; HYBRID ARCHITECTURE; PARAMETER SMOOTHING METHOD; TIME DELAY NEURAL NETWORK;

SPEECH RECOGNITION;

EID: 0030260670     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(96)00052-0     Document Type: Article

References (13)

1. M.W. Feng, F. Kubala, R. Schwarz and J. Markhoul (1988), "Improved speaker adaptation using text dependent spectral mappings", Proc. IEEE Internal. Conf. Acoust. Speech Signal Process., pp. 131-134.
2. Y. Komori (1991), "Time-state neural networks for phoneme identification by considering temporal structure of phonemic features", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., s.2.22.
3. K.F. Lee (1989), Automatic Speech Recognition: The Development of the SPHINX System (Kluwer Academic Publishers, Norwell, MA).
4. K.F. Lee and H.W. Hon (1989), "Speaker-independent phone recognition using hidden Markov models", IEEE Trans. Acoust. Speech Signal Process., Vol. 37, pp. 1641-1648.
5. W. Ma and D.V. Compernolle (1990), "TDNN labeling for a HMM recognizer", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., s.8.3.
6. N. Morgan and H. Bourlard (1990), "Continuous speech recognition using multilayer perceptrons with hidden Markov models", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., s.8.1.
7. J. Picone (1990), "Continuous speech recognition using hidden Markov models", IEEE Acoust. Speech Signal Process. Magazine, July, pp. 26-41.
8. L.R. Rabiner and B.H. Juang (1986), "An introduction to hidden Markov models", IEEE Acoust. Speech Signal Process. Magazine, January, pp. 4-16.
9. R. Schwarz et al. (1989), "Robust smoothing methods for discrete hidden Markov models", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., pp. 548-551.
10. H.P. Tseng, M.J. Sabin and E.A. Lee (1987), "Fuzzy vector quantization applied to hidden Markov modeling", Proc. IEEE Internat. Conf. Acoust Speech Signal Process., pp. 15.5.1-15.5.4.
11. A. Waibel (1989), "Modularity and scaling in large phonemic neural networks", IEEE Trans. Acoust. Speech Signal Process., Vol. 37, pp. 1888-1897.
12. A. Waibel et al. (1989a), "Phoneme recognition using time-delay neural networks", IEEE Trans. Acoust. Speech Signal Process., Vol. 37, pp. 328-339.
13. A. Waibel, H. Sawai and K. Shikano (1989b), "Consonant recognition by modular construction of large phonemic time-delay neural networks", Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., s.3.9.