10th Annual Conference of the International Speech Communication Association

Brighton, United Kingdom
September 6-10, 2009

Term-Dependent Confidence for Out-of-Vocabulary Term Detection

Dong Wang, Simon King, Joe Frankel, Peter Bell

University of Edinburgh, UK

Within a spoken term detection (STD) system, the decision maker plays an important role in retrieving reliable detections. Most of the state-of-the-art STD systems make decisions based on a confidence measure that is term-independent, which poses a serious problem for out-of-vocabulary (OOV) term detection. In this paper, we study a term-dependent confidence measure based on confidence normalisation and discriminative modelling, particularly focusing on its remarkable effectiveness for detecting OOV terms. Experimental results indicate that the term-dependent confidence provides much more significant improvement for OOV terms than terms in-vocabulary.

Full Paper

Bibliographic reference.  Wang, Dong / King, Simon / Frankel, Joe / Bell, Peter (2009): "Term-dependent confidence for out-of-vocabulary term detection", In INTERSPEECH-2009, 2139-2142.