ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Improving the recognition of names by document-level clustering

Bin Zhang, Wei Wu, Jeremy G. Kahn, Mari Ostendorf

Named entities are of great importance in spoken document processing, but speech recognizers often get them wrong because they are infrequent. A name correction method based on documentlevel name clustering is proposed in this paper, consisting of three components: named entity detection, name clustering, and name hypothesis selection. We compare the performance of this method to oracle conditions and show that the oracle gain is a 23% reduction in name character error for Mandarin and the automatic approach achieves about 20% of that.


doi: 10.21437/Interspeech.2009-319

Cite as: Zhang, B., Wu, W., Kahn, J.G., Ostendorf, M. (2009) Improving the recognition of names by document-level clustering. Proc. Interspeech 2009, 1035-1038, doi: 10.21437/Interspeech.2009-319

@inproceedings{zhang09b_interspeech,
  author={Bin Zhang and Wei Wu and Jeremy G. Kahn and Mari Ostendorf},
  title={{Improving the recognition of names by document-level clustering}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={1035--1038},
  doi={10.21437/Interspeech.2009-319}
}