| Weighting Phone Confidence Measures for Automatic Speech Recognition |
Title: Weighting Phone Confidence Measures for Automatic Speech Recognition
Author(s): Gies Bouwman, Lou Boves & Johan Koolwaaij
Reference: Proceedings of the COST249 Workshop on Voice Operated Telecom Services, Ghent, Belgium, pp. 59-62
Keywords: Confidence Measures
There is a PDF version (41420 bytes) available.
One of the most useful applications of Confidence Measures (CMs) in
Automatic Speech Recognition systems is early detection of incorrect
recognition hypotheses. A purely acoustic basis for such a CM is
particularly important when tracking errors resulting from Out of
Vocabulary speech, background noise or keyword substitution. A commonly
taken approach is to compute scores on subword units of the hypothesized
words and combine them in a word score. This paper investigates the
assumption that some subword types contain stronger distinctive
properties than others. Therefore, their scores ought to have a higher
contribution in the eventual word scores. Experiments in a connected
digit recognition task showed a relative Confidence Error Rate
improvement of 6% on word level and 11% on sentence level in comparison
to the baseline CM, with equal contribution of the phone confidence
scores.
Error processing SSI file