Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
10368491 | Computer Speech & Language | 2014 | 17 Pages |
Abstract
The results show that the possibilistic models provide significantly lower word error rate on the specialized domain task, where classical n-gram models fail due to the lack of training materials. For the broadcast news, the probabilistic models remain better than the possibilistic ones. However, a log-linear combination of the two kinds of models outperforms all the models used individually, which indicates that possibilistic models bring information that is not modeled by probabilistic ones.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Signal Processing
Authors
Stanislas Oger, Georges Linarès,