ISCA Archive Eurospeech 1997
ISCA Archive Eurospeech 1997

Estimation of global posteriors and forward-backward training of hybrid HMM/ANN systems

J. Hennebert, Christophe Ris, Hervè Bourlard, Steve Renals, Nelson Morgan

The results of our research presented in this paper are two-fold. First, an estimation of global posteriors is formalized in the framework of hybrid HMM/ANN systems. It is shown that hybrid HMM/ANN systems, in which the ANN part estimates local posteriors, can be used to modelize global model posteriors. This formalization provides us with a clear theory in which both REMAP and "classical" Viterbi trained hybrid systems are uni_ed. Second, a new forward- backward training of hybrid HMM/ANN systems is derived from the previous formulation. Comparisons of performance between Viterbi and forward- back- ward hybrid systems are presented and discussed.


doi: 10.21437/Eurospeech.1997-518

Cite as: Hennebert, J., Ris, C., Bourlard, H., Renals, S., Morgan, N. (1997) Estimation of global posteriors and forward-backward training of hybrid HMM/ANN systems. Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 1951-1954, doi: 10.21437/Eurospeech.1997-518

@inproceedings{hennebert97_eurospeech,
  author={J. Hennebert and Christophe Ris and Hervè Bourlard and Steve Renals and Nelson Morgan},
  title={{Estimation of global posteriors and forward-backward training of hybrid HMM/ANN systems}},
  year=1997,
  booktitle={Proc. 5th European Conference on Speech Communication and Technology (Eurospeech 1997)},
  pages={1951--1954},
  doi={10.21437/Eurospeech.1997-518},
  issn={1018-4074}
}