Estimation of Global Posteriors and Forward-Backward Training of Hybrid HMM/ANN Systems
| Art der Publikation: | Artikel in einem Konferenzbericht |
| Zitat: | henn97:euro |
| Buchtitel: | European Conference on Speech Communication and Technology (EUROSPEECH 97), Rhodes, Greece |
| Jahr: | 1997 |
| Seiten: | 1951-1954 |
| URL: | http://diuf.unifr.ch/people/he... |
| Abriss: | The results of our research presented in this paper is 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 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. |
| Schlagworte: | ANN, MLP, Speech Recognition |
| Autoren | |
| Hinzugefügt von: | [] |
| Gesamtbewertung: | 0 |
|
Anhänge
|
|
|
Notizen
|
|
|
|
|
|
Themen
|
|
|
|
|