Abstract | ||
---|---|---|
For many practical applications of speech recognition systems,it is desirable to have an estimate of confidence foreach hypothesized word, i.e. to have an estimate of whichwords of the output of the speech recognizer are likely to becorrect and which are not reliable. We describe the developmentof the measure of confidence tagger JANKA, which isable to provide confidence information for the words in theoutput of the speech recognizer JANUS-3-SR. On a spontaneousgerman human-to-human... |
Year | DOI | Venue |
---|---|---|
1997 | 10.1109/ICASSP.1997.596075 | ICASSP |
Keywords | Field | DocType |
spontaneous speech recognition,confidence measures,databases,natural languages,error correction,system testing,estimation theory,speech recognition,decoding,neural nets | Confidence measures,Computer science,Artificial intelligence,Natural language processing,Estimation theory,Artificial neural network,Pattern recognition,Speech recognition,Error detection and correction,Maximum likelihood linear regression,Natural language,Decoding methods,Word accuracy | Conference |
ISBN | Citations | PageRank |
0-8186-7919-0 | 60 | 11.00 |
References | Authors | |
7 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Thomas Schaaf | 1 | 364 | 44.96 |
T. Kemp | 2 | 60 | 11.34 |