Using phonetic features in unsupervised word decompounding for ASR with application to a less-represented language

@inproceedings{Pellegrini2007UsingPF,
  title={Using phonetic features in unsupervised word decompounding for ASR with application to a less-represented language},
  author={Thomas Pellegrini and Lori Lamel},
  booktitle={INTERSPEECH},
  year={2007}
}
In this paper, a data-driven word decompounding algorithm is described and applied to a broadcast news corpus in Amharic. The baseline algorithm has been enhanced in order to address the problem of increased phonetic confusability arising from word decompounding by incorporating phonetic properties and some constraints on recognition units derived from prior forced alignment experiments. Speech recognition experiments have been carried out to validate the approach. Out of vocabulary (OOV) words… CONTINUE READING

From This Paper

Figures, tables, results, and topics from this paper.

Key Quantitative Results

  • Out of vocabulary (OOV) words rates can be reduced by 30% to 40% and an absolute Word Error Rate (WER) reduction of 0.4% has been achieved.

References

Publications referenced by this paper.
Showing 1-10 of 12 references

Morphological Decomposition for Arabic Broadcast News Transcription

2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings • 2006
View 1 Excerpt

Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system

2004 IEEE International Conference on Acoustics, Speech, and Signal Processing • 2004
View 1 Excerpt

Similar Papers

Loading similar papers…