A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2014; you can also visit the original URL.
The file type is
Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers on XX - NAACL '07
We compare the effect of joint modeling of phonological features to independent feature detectors in a Conditional Random Fields framework. Joint modeling of features is achieved by deriving phonological feature posteriors from the posterior probabilities of the phonemes. We find that joint modeling provides superior performance to the independent models on the TIMIT phone recognition task. We explore the effects of varying relationships between phonological features, and suggest that in an ASRdoi:10.3115/1614108.1614112 fatcat:fbl5vr7u7behrksbihtknzipgq