Connectionist probability estimation in the DECIPHER speech recognition system
- 1 January 1992
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 601-604 vol.1
- https://doi.org/10.1109/icassp.1992.225837
Abstract
The authors have previously demonstrated that feedforward networks can be used to estimate local output probabilities in hidden Markov model (HMM) speech recognition systems (Renals et al., 1991). These connectionist techniques are integrated into the DECIPHER system, with experiments being performed using the speaker-independent DARPA RM database. The results indicate that: connectionist probability estimation can improve performance of a context-independent maximum-likelihood-trained HMM system; performance of the connectionist system is close to what can be achieved using (context-dependent) HMM systems of much higher complexity; and mixing connectionist and maximum-likelihood estimates can improve the performance of the state-of-the-art context-independent HMM systemKeywords
This publication has 5 references indexed in Scilit:
- Probability estimation by feed-forward networks in continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A probabilistic approach to the understanding and training of neural network classifiersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The decipher speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The ring array processor: A multiprocessing peripheral for connectionist applicationsJournal of Parallel and Distributed Computing, 1992
- A Stochastic Approximation MethodThe Annals of Mathematical Statistics, 1951