Paper: Investigations into the Crandem Approach to Word Recognition

ACL ID N10-1110
Title Investigations into the Crandem Approach to Word Recognition
Venue Human Language Technologies
Session Main Conference
Year 2010
Authors

We suggest improvements to a previously pro- posed framework for integrating Conditional Random Fields and Hidden Markov Models, dubbed a Crandem system (2009). The pre- vious authors’ work suggested that local la- bel posteriors derived from the CRF were too low-entropy for use in word-level automatic speech recognition. As an alternative to the log posterior representation used in their sys- tem, we explore frame-level representations derived from the CRF feature functions. We also describe a weight normalization transfor- mation that leads to increased entropy of the CRF posteriors. We report significant gains over the previous Crandem system on the Wall Street Journal word recognition task.