Joint versus independent phonological feature models within CRF phone recognition

Ilana Bromberg, Jeremy Morris, Eric Fosler-Lussier
2007 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American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers on XX - NAACL '07   unpublished
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 ASR
more » ... gest that in an ASR system, phonological features should be handled as correlated, rather than independent.
doi:10.3115/1614108.1614112 fatcat:fbl5vr7u7behrksbihtknzipgq