A phone recognizer helps to recognize words better

@inproceedings{Stemmer2003APR,
  title={A phone recognizer helps to recognize words better},
  author={Georg Stemmer and Viktor Zei\ssler and Christian Hacker and Elmar N{\"o}th and Heinrich Niemann},
  booktitle={ICASSP},
  year={2003}
}
For most speech recognition systems dynamic features are the only way to incorporate temporal context into the output distributions of the HMMs. In this paper we propose an efficient method to utilize a large context in the recognitio process. State scores of a phone recognizer which runs in parallel to the word recognizer are computed. Integrating these scores in the HMMs of the word recognizer makes their output densities context-dependent. The approach is evaluated on a set of spontaneous… CONTINUE READING
7 Citations
9 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-9 of 9 references

and P

  • S. Young, D. Kershaw, J. Odell, D. Ollason, V. Valtchev
  • Woodland, The HTK Book (for HTK Version 3.0…
  • 2000
1 Excerpt

Temporal Signal Processing for ASR

  • F. J. Smith
  • 1999

Temporal Signal Processing for ASR,” in Proceedings of the Automatic Speech Recognition and Understanding Workshop (ASRU’99

  • N. Morgan
  • 1999
1 Excerpt

and E

  • F. Gallwitz, M. Aretoulaki, +4 authors H. Niemann
  • Nöth, “The Erlangen Spoken Dialogue System EVAR…
  • 1998
1 Excerpt

and O

  • M. Ostendorf, V. Digalakis
  • Kimball, “From HMMs to Segment Models: A Unified…
  • 1996
1 Excerpt

From HMMs to Segment Models : A Unified View of Stochastic Modeling for Speech Recognition

  • V. Valtchev, P. Woodland
  • IEEE Trans . on Speech and Audio Processing

Similar Papers

Loading similar papers…