Please use this identifier to cite or link to this item:
|Title:||Probabilistic state clustering using conditional random field for context-dependent acoustic modelling|
Conditional random field
|Source:||Sim, K.C. (2010). Probabilistic state clustering using conditional random field for context-dependent acoustic modelling. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 : 70-73. ScholarBank@NUS Repository.|
|Abstract:||Hidden Markov Models are widely used in speech recognition systems. Due to the co-articulation effects of continuous speech, context-dependent models have been found to yield performance improvements. One major issue with context-dependent acoustic modelling is the robust parameter estimation of unseen or rare models in the training data. Typically, decision tree state clustering is used to ensure that there are sufficient data for each physical state. Decision trees based on phonetic questions are used to cluster the states. In this paper, conditional random field (CRF) is used to perform probabilistic state clustering where phonetic questions are used as binary feature functions to predict the latent cluster weights. Experimental results on the Wall Street Journal reveals that CRF-based state clustering outperformed the conventional maximum likelihood decision tree state clustering with similar model complexities by about 10% relative. © 2010 ISCA.|
|Source Title:||Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Dec 9, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.