Unsupervised word segmentation from noisy input

@article{Heymann2013UnsupervisedWS,
  title={Unsupervised word segmentation from noisy input},
  author={Jahn Heymann and Oliver Walter and Reinhold H{\"a}b-Umbach and Bhiksha Raj},
  journal={2013 IEEE Workshop on Automatic Speech Recognition and Understanding},
  year={2013},
  pages={458-463}
}
In this paper we present an algorithm for the unsupervised segmentation of a character or phoneme lattice into words. Using a lattice at the input rather than a single string accounts for the uncertainty of the character/phoneme recognizer about the true label sequence. An example application is the discovery of lexical units from the output of an error-prone phoneme recognizer in a zero-resource setting, where neither the lexicon nor the language model is known. Recently a Weighted Finite… CONTINUE READING
Highly Cited
This paper has 23 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 17 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 14 references

latticelm

  • G. Neubig
  • Apr. 2013.
  • 2013
Highly Influential
7 Excerpts

Similar Papers

Loading similar papers…