Towards Using Hierarchical Posteriors for Flexible Automatic Speech Recognition Systems

@inproceedings{Bourlard2004TowardsUH,
  title={Towards Using Hierarchical Posteriors for Flexible Automatic Speech Recognition Systems},
  author={Herv{\'e} Bourlard and Samy Bengio and Mathew Magimai Doss and Qifeng Zhu and Bertrand Mesot and Nelson Morgan},
  year={2004}
}
Local state (or phone) posterior probabilities are often investigated as local classifiers (e.g., hybrid HMM/ANN systems) or as transformed acoustic features (e.g., “TANDEM”) towards improved speech recognition systems. In this paper, we present initial results towards boosting these approaches by improving the local state, phone, or word posterior estimates, using all possible acoustic information (as available in the whole utterance), as well as possible prior information (such as topological… CONTINUE READING
Highly Cited
This paper has 39 citations. REVIEW CITATIONS

References

Publications referenced by this paper.
Showing 1-10 of 26 references

N.,Connectionist Speech Recognition – A Hybrid Approach

  • H. Bourlard, Morgan
  • Kluwer Academic Publishers,
  • 1994
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…