Abstract
This paper describes the investigation of possibilities for using self organizing feature maps in connection with Hidden Markov Modeling (HMM) in order to build a Neural Network based continuous speech recognition system. Starting with a brief outline of the problems arising with the use of Neural Networks for continuous speech recognition and the various attempts in order to solve these problems, the motivation for using self organizing feature maps in combination with Hidden Markov Models is explained. The various aspects and interpretations resulting from that approach are discussed. A description of the details that have to be considered during the design of the feature map and which seem to be of special importance for the use in combination with a Markov model is given. The results obtained with that approach are evaluated and compared to the performance obtained with the use of ordinary HMM based speech recognition algorithms. A final evaluation of the basic idea and conclusions resulting in recommendations for future research directions are given at the end of the paper.
Preview
Unable to display preview. Download preview PDF.
References
T. Kohonen: The "Neural" Phonetic Typewriter, IEEE Computer, Special Issue on Neural Computing, March 1988, pp. 11–22
T. Kohonen, K. Mäkisara, T. Saramäki: Phonotopic Maps — Insightful Representation of Phonological Features for Speech Recognition, Proc. 7th ICPR, Montreal, 1984, pp. 182–185
T. Kohonen, K. Torkkola, m. Shozakai, J. Kangas, O. Ventä: Phonetic Typewriter for Finnish and Japanese, Proc. IEEE-ICASSP, New York, 1988, pp. 607–610
A. Waibel, T. Hanazwa, G. Hinton, K. Shikano, K. Lang: Phoneme Recognition: Neural Networks vs. Hidden Markov Models, Proc. IEEE-ICASSP, New York, 1988, pp. 107–110
L.E. Atlas, T. Homma, R.J. Marks: A Neural Network Model for Vowel Classification, Proc. IEEE-ICASSP, Dallas, 1987
M.L. Rossen, J.A. Anderson: Representational Issues in a Neural Network Model of Syllable Recognition, Proc. Int. Joint Conf. on Neural Networks, Washington, 1989, pp. I-19–I-24
B. Gold, R.P. Lippman: A Neural Network for Isolated-Word Recognition, Proc. IEEE-ICASSP, New York, 1988, pp. 44–47
M.A. Franzini, M.J. Witbrock, K.F. Lee: Speaker-Independent Recognition of Connected Utterances Using Recurrent and Non-recurrent Neural Networks, Proc. Int. Joint Conf. on Neural Networks, Washington, 1989, pp. II-1–II-5
M. Gori, Y. Bengio, R. De Mori: BPS: A Learning Algorithm for Capturing the Dynamic Nature of Speech, Proc. Int. Joint Conf. on Neural Networks, Washington, 1989, pp. II-417–II-423
P. Brauer, P. Knagenhjelm: Infrastructure in Kohonen Maps, Proc. IEEE-ICASSP, Glasgow, 1989, pp. 647–650
L.R. Bahl, P.F. Brown, P.V. de Souza, R.L. Mercer: Maximum Mutual Information Estimation of Hidden Markov Model Parameters for Speech Recognition, Proc. IEEE-ICASSP, Tokyo, 1986, pp. 49–52
S. Hafner: Neural Networks in Speech Recognition, Diploma Thesis, University of Stuttgart, 1989 (in German)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rigoll, G. (1990). Neural network based continuous speech recognition by combining self organizing feature maps and Hidden Markov Modeling. In: Almeida, L.B., Wellekens, C.J. (eds) Neural Networks. EURASIP 1990. Lecture Notes in Computer Science, vol 412. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-52255-7_41
Download citation
DOI: https://doi.org/10.1007/3-540-52255-7_41
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-52255-3
Online ISBN: 978-3-540-46939-1
eBook Packages: Springer Book Archive