Abstract | ||
---|---|---|
We suggest improvements to a previously proposed framework for integrating Conditional Random Fields and Hidden Markov Models, dubbed a Crandem system (2009). The previous authors' work suggested that local label 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 system, we explore frame-level representations derived from the CRF feature functions. We also describe a weight normalization transformation 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. |
Year | Venue | Keywords |
---|---|---|
2010 | HLT-NAACL | hidden markov models,previous crandem system,crf posterior,wall street journal word,crandem system,word recognition,crandem approach,previous author,conditional random fields,crf feature function,word-level automatic speech recognition,recognition task |
Field | DocType | ISBN |
Conditional random field,Normalization (statistics),Computer science,Word recognition,Speech recognition,Natural language processing,Artificial intelligence,Hidden Markov model,Machine learning | Conference | 1-932432-65-5 |
Citations | PageRank | References |
2 | 0.40 | 8 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rohit Prabhavalkar | 1 | 163 | 22.56 |
Preethi Jyothi | 2 | 57 | 7.85 |
William Hartmann | 3 | 64 | 10.66 |
J. Morris | 4 | 44 | 4.12 |
Eric Fosler-Lussier | 5 | 690 | 66.40 |