Recurrent network automata for speech recognition: a summary of recent work
- 17 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 241-248
- https://doi.org/10.1109/nnsp.1994.366043
Abstract
The integration of hidden Markov models (HMMs) and neural networks is an important research line to obtain new speech recognition systems that combine a good time-alignment capability and a powerful discrimination-based training. The recurrent network automata (RNA) model is a hybrid of a recurrent neural network, which estimates the state emission probability of a HMM, and a dynamic programming, which finds the best state sequence. This paper reports the results obtained with the RNA model, after three years of research and application in speaker independent digit recognition over the public telephone network.Keywords
This publication has 10 references indexed in Scilit:
- Word recognition with recurrent network automataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Correlative training and recurrent network automata for speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Connectionist Viterbi training: a new hybrid method for continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Reduced channel dependence for speech recognitionPublished by Association for Computational Linguistics (ACL) ,1992
- Speech recognition using segmental neural netsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- HMM modeling in the public telephone network environment: experiments and resultsPublished by International Speech Communication Association ,1991
- An enhancement to MLP model to enforce closed decision regionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Continuous speech recognition with the connectionist Viterbi training procedure: a summary of recent workPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Integrating time alignment and neural networks for high performance continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Links between Markov models and multilayer perceptronsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990