ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

A spontaneous speech recognition algorithm using word trigram models and filled-pause procedure

Jin'ichi Murakami, Shoichi Matsunaga

This paper describes an effective recognition algorithm that uses word trigram models directly and a procedure for dealing with filled-pauses in spontaneous speech. This recognition algorithm greatly reduces the memory requirements and computational costs by employing two techniques: beam search and an improved Viterbi search. With these methods, execution can be performed in a 15M byte space for about a 1500-word vocabulary. The filled-pause procedure, capable of handing many filled-pauses in spontaneous speech, is then examined for spontaneous speech recognition. Even though the proposed algorithm employs a simple procedure, a 42% sentence recognition rate is obtained for spontaneous speech. Including the semantically correct sentences, the sentence recognition rate is about 15%.


Cite as: Murakami, J., Matsunaga, S. (1994) A spontaneous speech recognition algorithm using word trigram models and filled-pause procedure. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 819-822

@inproceedings{murakami94_icslp,
  author={Jin'ichi Murakami and Shoichi Matsunaga},
  title={{A spontaneous speech recognition algorithm using word trigram models and filled-pause procedure}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={819--822}
}