Relating frame accuracy with word error in hybrid ANN-HMM ASR

@inproceedings{Shire2001RelatingFA,
  title={Relating frame accuracy with word error in hybrid ANN-HMM ASR},
  author={Michael L. Shire},
  booktitle={INTERSPEECH},
  year={2001}
}
Frame accuracy is a common and natural summary statistic to use in neural-network-based ASR. It is often used as an indication of the performance of the neural network probability estimator and in the stopping criterion during its training. Though considered an important factor for word recognition, the frame accuracy presents an incomplete and sometimes deficient indicator of performance for the overall task of word recognition, as with many such summary statistics. Many in the ASR community… CONTINUE READING
2 Citations
6 References
Similar Papers

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-6 of 6 references

Numbers corpus, release 1.0

  • Center for Spoken Language Understanding, Department of Computer Science, Engineering, Oregon Graduate Institute
  • 1995.
  • 1995
1 Excerpt

Connectionist Speech Recognition- A Hybrid Approach

  • Hervé Bourlard, Nelson Morgan
  • 1994
1 Excerpt

Similar Papers

Loading similar papers…