Abstract
Because of the application of the Hidden Markov Model (HMM) in acoustic modeling, a significant breakthrough has been made in recognizing continuous speech with a large glossary. However, some unreasonable hypotheses for acoustic modeling and the unclassified training algorithm on which the HMM based form a bottleneck, restricting the further improvement in speech recognition. The Artificial Neural Network (ANN) techniques can be adopted as an alternative modeling paradigm. By means of the weight values of the network connections, neural networks can steadily store the knowledge acquired from the training process. But they possess a weak memory, not being suitable to store the instantaneous response to various input modes. To overcome the flaws of the HMM paradigm, we design a hybrid HMM/ANN model. In this hybrid model, the nonparametric probabilistic model (a BP neural network) is used to substitute the Gauss blender to calculate the observed probability which is necessary for computing the states of the HMM model. To optimizing the network structure in and after the training process, we propose an algorithm to prune hidden nodes in a trained neural network, and utilize the generalized Hebbian algorithm to reconfigure the parameters of the network. Some experiments show that the hybrid model has a good performance in speech recognition.
Chapter PDF
Similar content being viewed by others
References
Xiongwei Zhang, Liang Chen, and Jinbin Yang Modern Speech technology and applications, China Machine Press 2003.8 ISBN.7-1111-12795-1 219–222
Jinhui Xie, Hidden Markov Model and its applications in speech processing, HuaZhong University Press, 1995.4 ISBN 7-5609-1094-7/TN.34 103–113
Changning Huang, Ying Xia, Monograph of speech information processing [A], TSingHua University Press, 1996.4 ISBN7-302-01929-0/TP.879 489–508
Tingyue Zhuang, Yunhe Pan and Fei Wu, Web-based Multimedia Information Analysis and Retrieve TsingHua Unversity Press 2002.9 ISBN 7-302-05584-X/TP.3299 122–272
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 International Federation for Information Processing
About this paper
Cite this paper
Xi, X., Lin, K., Zhou, C., Cai, J. (2005). A New Hybrid Hmm/Ann Model for Speech Recognition. In: Li, D., Wang, B. (eds) Artificial Intelligence Applications and Innovations. AIAI 2005. IFIP — The International Federation for Information Processing, vol 187. Springer, Boston, MA. https://doi.org/10.1007/0-387-29295-0_24
Download citation
DOI: https://doi.org/10.1007/0-387-29295-0_24
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-28318-0
Online ISBN: 978-0-387-29295-3
eBook Packages: Computer ScienceComputer Science (R0)