ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Acceleration of spoken term detection using a suffix array by assigning optimal threshold values to sub-keywords

Kouichi Katsurada, Seiichi Miura, Kheang Seng, Yurie Iribe, Tsuneo Nitta

We previously proposed a fast spoken term detection method that uses a suffix array data structure for searching large-scale speech documents. The method reduces search time via techniques such as keyword division and iterative lengthening search. In this paper, we propose a statistical method of assigning different threshold values to sub-keywords to further accelerate search. Specifically, the method estimates the numbers of results for keyword searches and then reduces them by adjusting the threshold values assigned to sub-keywords. We also investigate the theoretical condition that must be satisfied by these threshold values. Experiments show that the proposed search method is 10% to 30% faster than previous methods.


doi: 10.21437/Interspeech.2013-3

Cite as: Katsurada, K., Miura, S., Seng, K., Iribe, Y., Nitta, T. (2013) Acceleration of spoken term detection using a suffix array by assigning optimal threshold values to sub-keywords. Proc. Interspeech 2013, 11-14, doi: 10.21437/Interspeech.2013-3

@inproceedings{katsurada13_interspeech,
  author={Kouichi Katsurada and Seiichi Miura and Kheang Seng and Yurie Iribe and Tsuneo Nitta},
  title={{Acceleration of spoken term detection using a suffix array by assigning optimal threshold values to sub-keywords}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={11--14},
  doi={10.21437/Interspeech.2013-3}
}