ISCA Archive Interspeech 2005
ISCA Archive Interspeech 2005

Minimum Bayes-risk decoding considering word significance for information retrieval system

Hiroaki Nanjo, Teruhisa Misu, Tatsuya Kawahara

The paper addresses a new evaluation measure of automatic speech recognition (ASR) and a decoding strategy oriented for speech-based information retrieval (IR). Although word error rate (WER), which treats all words in a uniform manner, has been widely used as an evaluation measure of ASR, significance of words are different in speech understanding or IR. In this paper, we define a new ASR evaluation measure, namely, weighted word error rate (WWER) that gives a weight on errors from a viewpoint of IR. Then, we formulate a decoding method to minimize WWER based on Minimum Bayes-Risk (MBR) framework, and show that the decoding method improves WWER and IR accuracy.


doi: 10.21437/Interspeech.2005-341

Cite as: Nanjo, H., Misu, T., Kawahara, T. (2005) Minimum Bayes-risk decoding considering word significance for information retrieval system. Proc. Interspeech 2005, 561-564, doi: 10.21437/Interspeech.2005-341

@inproceedings{nanjo05_interspeech,
  author={Hiroaki Nanjo and Teruhisa Misu and Tatsuya Kawahara},
  title={{Minimum Bayes-risk decoding considering word significance for information retrieval system}},
  year=2005,
  booktitle={Proc. Interspeech 2005},
  pages={561--564},
  doi={10.21437/Interspeech.2005-341}
}