Paper Info
Title
Continuous speech recognition using dynamic Bayesian networks: A fast decoding algorithm
Abstract
State-of-the-art automatic speech recognition systems are based on probabilistic modeling of the speech signal using Hidden Markov Models (HMMs). Recent work has focused on the use of dynamic Bayesian networks (DBNs) framework to construct new acoustic models to overcome the limitations of HMM based systems. In this line of research we proposed a methodology to learn the conditional independence assertions of acoustic models based on structural learning of DBNs. In previous work, we evaluated this approach for simple isolated and connected digit recognition tasks. In this paper we evaluate our approach for a more complex task: continuous phoneme recognition. For this purpose, we propose a new decoding algorithm based on dynamic programming. The proposed algorithm decreases the computational complexity of decoding and hence enables the application of the approach to complex speech recognition tasks.
Year
DOI
Venue
2002
10.1007/978-3-540-39879-0_16
ADVANCES IN BAYESIAN NETWORKS
Keywords
Field
DocType
dynamic bayesian network,speech recognition,dynamic bayesian networks
Computer science,Artificial intelligence,Probabilistic logic,Dynamic programming,Conditional independence,Algorithm,Speech recognition,Bayesian network,Decoding methods,Hidden Markov model,Machine learning,Dynamic Bayesian network,Computational complexity theory
Conference
Volume
ISSN
Citations 
146
1434-9922
2
PageRank 
References 
Authors
0.47
10
2
Name
Order
Citations
PageRank
Murat Deviren1264.65
Khalid Daoudi214523.68