Finding consensus among words: lattice-based word error minimization

  title={Finding consensus among words: lattice-based word error minimization},
  author={Lidia Mangu and Eric Brill and Andreas Stolcke},
We describe a new algorithm for finding the hypothesis in a recognition lattice that is expected to minimize the word er ror 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 le ad 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… CONTINUE READING
Highly Influential
This paper has highly influenced 15 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 292 citations. REVIEW CITATIONS

4 Figures & Tables



Citations per Year

293 Citations

Semantic Scholar estimates that this publication has 293 citations based on the available data.

See our FAQ for additional information.