September 22-25, 1997
For many practical applications of speech recognition systems, it is desirable to have an estimate of confidence for each hypothesized word, i.e. to have an estimate which words of the speech recognizer's output are likely to be correct and which are not reliable. Many oftoday's speech recognition systems use word lattices as a compact representation of a set of alternative hypothesis. We exploit the use of such word lattices as information sources for the measure-of- confidence tagger JANKA . In experiments on spontaneous human- to-human speech data the use of word lattice related information significantly improves the tagging accuracy.
Bibliographic reference. Kemp, Thomas / Schaaf, Thomas (1997): "Estimating confidence using word lattices", In EUROSPEECH-1997, 827-830.