Probability Estimation by Feed-Forward Networks in Continuous Speech Recognition
Title | Probability Estimation by Feed-Forward Networks in Continuous Speech Recognition |
Publication Type | Technical Report |
Year of Publication | 1991 |
Authors | Renals, S., Morgan N., & Bourlard H. |
Other Numbers | 660 |
Abstract | We review the use of feed-forward networks as estimators of probability densities in hidden Markov modeling. In this paper we are mostly concerned with radial basis functions (RBF) networks. We note the isomorphism of RBF networks to tied mixture density estimators; additionally we note that RBF networks are trained to estimate posteriors rather than the likelihoods estimated by tied mixture density estimators. We show how the neural network training should be modified to resolve this mismatch. We also discuss problems with discriminative training, particularly the problem of dealing with unlabeled training data and the mismatch between model and data priors. |
URL | http://www.icsi.berkeley.edu/ftp/global/pub/techreports/1991/tr-91-030.pdf |
Bibliographic Notes | ICSI Technical Report TR-91-030 |
Abbreviated Authors | S. Renals, N. Morgan, and H. Bourlard |
ICSI Research Group | Speech |
ICSI Publication Type | Technical Report |