We previously proposed [1] fast spoken term detection that uses a suffix array as a data structure for searching a large-scale speech documents. In this method, a keyword is divided into sub-keywords, and the phoneme sequences that contain two or more sub-keywords are output as results. Although the search is executed very quickly on a 10,000-h speech database, we only proposed a variety of matching procedures in [1]. In this paper, we compare different varieties of matching procedures in which the number of phonemes in a sub-keyword and the required number of sub-keywords to be contained in a search result are different. We also compare the performance and the process time of our method with typical spoken term detection using an inverted index.

Katsurada, K., Teshima, S. and Nitta, T., “Fast Keyword Detection Using Suffix Array”, InterSpeech2009, pp.2147-2150, 2009

@inproceedings{katsurada11_interspeech,
  title     = {{Evaluation of fast spoken term detection using a suffix array}},
  author    = {Kouichi Katsurada and Shinta Sawada and Shigeki Teshima and Yurie Iribe and Tsuneo Nitta},
  year      = {2011},
  booktitle = {{Interspeech 2011}},
  pages     = {909--912},
  doi       = {10.21437/Interspeech.2011-353},
  issn      = {2958-1796},
}