Title
A comparative study on various confidence measures in large vocabulary speech recognition
Abstract
In this paper, we have conducted a comparative study on several confidence measures (CM) for large vocabulary speech recognition. Firstly, we propose a novel high-level CM that is based on the inter-word mutual information (MI). Secondly, we experimentally investigate several popular low-level CM, such as word posterior probabilities, N-best counting, likelihood ratio testing (LRT), etc. Finally, we have studied a simple linear interpolation strategy to combine the best low-level CM with the best high-level CM. All of these CM are examined in two large vocabulary ASR tasks, namely the Switchboard task and a Mandarin dictation task, to verify the recognition errors in baseline recognition systems. Experimental results show: (1) the proposed MI-based CM greatly surpass another existing high-level CM which are based on the LSA technique; (2) among all low-level CM, word posteriori probabilities give the best verification performance; (3) when combining the word posteriori probabilities with the MI-based CM, the equal error rate is reduced from 24.4% to 23.9% in the Switchboard task and from 17.5% to 16.2% in the Mandarin dictation task.
Year
DOI
Venue
2004
10.1109/CHINSL.2004.1409573
ISCSLP
Keywords
Field
DocType
switchboard task,speech recognition,interpolation,maximum likelihood estimation,vocabulary,lsa technique,large vocabulary speech recognition,equal error rate,word posterior probabilities,high-level confidence measures,inter-word mutual information,linear interpolation,asr,verification performance,likelihood ratio testing,n-best counting,baseline recognition systems,recognition errors,error statistics,mandarin dictation task,posterior probability,likelihood ratio test,comparative study,mutual information
Pattern recognition,Computer science,Interpolation,Word error rate,Speech recognition,Posterior probability,Dictation,Mutual information,Artificial intelligence,Linear interpolation,Vocabulary,Mandarin Chinese
Conference
ISBN
Citations 
PageRank 
0-7803-8678-7
16
1.02
References 
Authors
5
4
Name
Order
Citations
PageRank
Gang Guo1161.02
Chao Huang221823.06
Hui Jiang31493113.16
Ren-Hua Wang434441.36