ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

Finding consensus among words: lattice-based word error minimization

Lidia Mangu, Eric Brill, Andreas Stolcke

We describe a new algorithm for finding the hypothesis in a recognition lattice that is expected to minimize the word error rate (WER). Our approach thus overcomes the mismatch between the word-based performance metric and the standard MAP scoring paradigm that is sentence-based, and that can lead to sub-optimal recognition results. To this end we first find a complete alignment of all words in the recognition lattice, identifying mutually supporting and competing word hypotheses. Finally, a new sentence hypothesis is formed by concatenating the words with maximal posterior probabilities. Experimentally, this approach leads to a significant WER reduction in a large vocabulary recognition task.


doi: 10.21437/Eurospeech.1999-127

Cite as: Mangu, L., Brill, E., Stolcke, A. (1999) Finding consensus among words: lattice-based word error minimization. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 495-498, doi: 10.21437/Eurospeech.1999-127

@inproceedings{mangu99_eurospeech,
  author={Lidia Mangu and Eric Brill and Andreas Stolcke},
  title={{Finding consensus among words: lattice-based word error minimization}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={495--498},
  doi={10.21437/Eurospeech.1999-127}
}