ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

CRANDEM: conditional random fields for word recognition

Jeremy Morris, Eric Fosler-Lussier

To date, the use of Conditional Random Fields (CRFs) in automatic speech recognition has been limited to the tasks of phone classification and phone recognition. In this paper, we present a framework for using CRF models in a word recognition task that extends the well-known Tandem HMM framework to CRFs. We show results that compare favorably to a set of standard baselines, and discuss some of the benefits and potential pitfalls of this method.

doi: 10.21437/Interspeech.2009-569

Cite as: Morris, J., Fosler-Lussier, E. (2009) CRANDEM: conditional random fields for word recognition. Proc. Interspeech 2009, 3063-3066, doi: 10.21437/Interspeech.2009-569

  author={Jeremy Morris and Eric Fosler-Lussier},
  title={{CRANDEM: conditional random fields for word recognition}},
  booktitle={Proc. Interspeech 2009},