Crandem systems: Conditional random field acoustic models for hidden Markov models

Eric Fosler-Lussier, Jeremy Morris

Abstract

In recent years, Conditional Random Fields (CRFs) have been examined as a statistical model for speech recognition. In this paper, we explore the use of features derived via CRFs as inputs to a Tandem-style HMM ASR system (that is, a Crandem system). We present a model for deriving frame-level posterior features via CRFs to use in Crandem modeling and additionally provide experimental results that show the Crandem system can slightly significantly outperform both a comparable Tandem system and a comparable CRF system on the task of phone recognition.
BibTeX
@inproceedings{foslerlussier2008crandem,
  author = {Eric Fosler-Lussier and Jeremy Morris},
  title = {{Crandem systems: Conditional random field acoustic models for hidden Markov models}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2008},
  doi = {10.1109/icassp.2008.4518543},
}

Loading related content...

Figure