Continuous Speech Recognition Using Dynamic Bayesian Networks : A Fast Decoding Algorithm

Murat Deviren 1 Khalid Daoudi 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
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.
Document type :
Book sections
Complete list of metadatas

https://hal.inria.fr/inria-00100260
Contributor : Publications Loria <>
Submitted on : Tuesday, September 26, 2006 - 10:16:30 AM
Last modification on : Thursday, January 11, 2018 - 6:19:55 AM

Identifiers

  • HAL Id : inria-00100260, version 1

Collections

Citation

Murat Deviren, Khalid Daoudi. Continuous Speech Recognition Using Dynamic Bayesian Networks : A Fast Decoding Algorithm. Gamez, José and Moral, Serafin and Salmeron, Antonio. Advances in Bayesian Networks, Springer Physica Verlag, pp.289-307, 2004, Studies in Fuzziness and Soft Computing. ⟨inria-00100260⟩

Share

Metrics

Record views

197