Name
Title | ||
|---|---|---|
Knowledge-Based Adaptive Decision Tree State Tying for Conversational Speech Recognition |
Abstract | ||
|---|---|---|
This paper presents a new method of constructing phonetic decision trees (PDTs) for acoustic model state tying based on implicitly induced prior knowledge. Our hypothesis is that knowledge on pronunciation variation in spontaneous, conversational speech contained in a relatively large corpus can be used for building domain-specific or speaker-dependent PDTs. In view of tree-structure adaptation, this method leads to transformation of tree topology in contrast to keeping fixed tree structure as in traditional methods of speaker adaptation. A Bayesian learning framework is proposed to incorporate prior knowledge on decision rules in a greedy search of new decision trees, where the prior is generated by a decision tree growing process on a large data set. Experimental results on the telemedicine automatic captioning task demonstrate that the proposed approach results in consistent improvement in model quality and recognition accuracy. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/TASL.2007.901830 | IEEE Transactions on Audio, Speech & Language Processing |
Keywords | Field | DocType |
tree topology,telemedicine automatic captioning task,large data,acoustic modeling,belief networks,speech processing,decision tree state tying,state tying,speech recognition,new decision tree,conversational speech recognition,pronunciation variation,learning (artificial intelligence),decision rule,decision rules,knowledge-based adaptive phonetic decision tree structure,prior knowledge,approximate bayesian,acoustic model state tying,speaker recognition,knowledge-based adaptive decision tree,tree topology transformation,tree structure,fixed tree structure,large corpus,decision tree,implicit prior,speaker adaptation,decision trees,acoustic model state,phonetic decision tree,greedy search,bayesian learning framework,hidden markov models,learning artificial intelligence,bayesian learning,knowledge base,knowledge based systems | Decision tree,Computer science,Speaker recognition,Tree structure,Artificial intelligence,Natural language processing,Decision rule,Pattern recognition,Knowledge-based systems,Speech recognition,Machine learning,Decision tree learning,Acoustic model,Incremental decision tree | Journal |
Volume | Issue | ISSN |
15 | 7 | 1558-7916 |
Citations | PageRank | References |
2 | 0.42 | 17 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rusheng Hu | 1 | 21 | 2.54 |
| Yunxin Zhao | 2 | 807 | 121.74 |