ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

A posterior probability-based system hybridisation and combination for spoken term detection

Javier Tejedor, Dong Wang, Simon King, Joe Frankel, José Colás

Spoken term detection (STD) is a fundamental task for multimedia information retrieval. To improve the detection performance, we have presented a direct posterior-based confidence measure generated from a neural network. In this paper, we propose a detection-independent confidence estimation based on the direct posterior confidence measure, in which the decision making is totally separated from the term detection. Based on this idea, we first present a hybrid system which conducts the term detection and confidence estimation based on different sub-word units and then propose a combination method which merges detections from heterogeneous term detectors based on the direct posterior-based confidence. Experimental results demonstrated that the proposed methods improved system performance considerably for both English and Spanish.


doi: 10.21437/Interspeech.2009-609

Cite as: Tejedor, J., Wang, D., King, S., Frankel, J., Colás, J. (2009) A posterior probability-based system hybridisation and combination for spoken term detection. Proc. Interspeech 2009, 2131-2134, doi: 10.21437/Interspeech.2009-609

@inproceedings{tejedor09_interspeech,
  author={Javier Tejedor and Dong Wang and Simon King and Joe Frankel and José Colás},
  title={{A posterior probability-based system hybridisation and combination for spoken term detection}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={2131--2134},
  doi={10.21437/Interspeech.2009-609}
}