The work describes a method for generating back-off models for context-dependent unit modeling. The main characteristic of the approach is that of building generic models by gathering statistics of detailed models, collected during Baum-Welch reestimation. The construction of back-off models does not require additional processing of the training data, allowing to quickly build different models sets with different back-off criteria starting from the same set of trained models and their statistics
Model Agglomeration for Context-Dependent Acoustic Modeling
Brugnara, Fabio
2001-01-01
Abstract
The work describes a method for generating back-off models for context-dependent unit modeling. The main characteristic of the approach is that of building generic models by gathering statistics of detailed models, collected during Baum-Welch reestimation. The construction of back-off models does not require additional processing of the training data, allowing to quickly build different models sets with different back-off criteria starting from the same set of trained models and their statisticsFile in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
