|
Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1842/1212
|
| Title: | Estimation of global posteriors and forward-backward training of hybrid HMM/ANN systems. |
| Authors: | Hennebert, J
Ris, C
Bourlard, Herve
Renals, Steve
Morgan, Nelson |
| Issue Date: | 1997 |
| Citation: | In Proc. Eurospeech, pages 1951-1954, Rhodes, 1997. |
| Publisher: | International Speech Communication Association |
| Abstract: | 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 model global posteriors. This formalization provides us with a clear theory in which both REMAP and ``classical'' Viterbi trained hybrid systems are unified. Second, a new forward-backward training of hybrid HMM/ANN systems is derived from the previous formulation. Comparisons of performance between Viterbi and forward-backward hybrid systems are presented and discussed. |
| URI: | http://hdl.handle.net/1842/1212 |
| Appears in Collections: | CSTR publications
|
Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.
|
