ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Keyword and phrase spotting with heuristic language model

Tatsuya Kawahara, Toshihiko Munetsugu, Norihide Kitaoka, Shuji Doshita

We discuss on a word spotting strategy that incorporates a language model as heuristics. It judges the word existence based on not only the matching score of the word itself but also the plausibility of the rest part as a sentence. Several language models are examined with respect to the accuracy and robustness, and the followings are conclusions: (1) Syllable-level knowledge is robust but insufficient. (2) Word-level knowledge is very effective and robust against spontaneous speech. (3) Word-pair constraint is most powerful but not robust. We further propose to incorporate phrase-level syntax into the spotting unit. The phrase-level syntax is rarely violated even in spontaneous utterances and significantly reduces the task perplexity. It turned out effective especially in getting a higher detection rate with a small number of false alarms.


Cite as: Kawahara, T., Munetsugu, T., Kitaoka, N., Doshita, S. (1994) Keyword and phrase spotting with heuristic language model. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 815-818

@inproceedings{kawahara94_icslp,
  author={Tatsuya Kawahara and Toshihiko Munetsugu and Norihide Kitaoka and Shuji Doshita},
  title={{Keyword and phrase spotting with heuristic language model}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={815--818}
}