This method makes it possible to handle mixture Gaussian HMMs in the decision tree based state tying algorithm, and provides a higher recognition performance ...
This paper has presented an effective approach to synthe- sizing mixture Gaussian distributions in decision tree based state tying. This method makes it ...
This method makes it possible to handle mixture Gaussian HMMs in the decision tree based state tying algorithm, and provides a higher recognition performance ...
In this paper we report some novel techniques for using LDMs as context- dependent phone models. 1.1. LDMs as models of speech. The attraction of LDMs is their ...
An efficient mixture Gaussian synthesis method for decision tree based state tying that produces better context-dependent models in a short period of ...
The first method gives optimal threshold values for stop criteria in decision tree growing, and the second uses an additional condition in the question ...
... Another common approach to state clustering makes use of decision trees by asking questions about the left and right contexts for each trigraph. With the ...
We present two approaches of using multiple-mixture. Gaussian parameterization to improve the likelihood evaluation function in decision tree node splitting.
In the decision-tree-based state tying, decision trees are phonetic binary trees in which a yes/no phonetic question is attached to each node. Initially, all ...
This paper de- scribes a method of creating a tied-state continuous speech recognition system using a phonetic decision tree. This tree- based clustering is ...
Missing: synthesis | Show results with:synthesis