Inverted HMM-a Proof of Concept

@inproceedings{Doetsch2016InvertedHP,
  title={Inverted HMM-a Proof of Concept},
  author={Patrick Doetsch and Stefan Hegselmann and Ralf Schl{\"u}ter and Hermann Ney},
  year={2016}
}
In this work, we propose an inverted hidden Markov model (HMM) approach to automatic speech and handwriting recognition that naturally incorporates discriminative, artificial neural network based label distributions. Instead of aligning each input frame to a state label as in the standard HMM derivation, we propose to inversely align each element of an HMM state label sequence to a single input frame. This enables an integrated discriminative model that may be trained end-to-end from scratch or… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 21 references

Long Short-Term Memory

Neural Computation • 1997
View 4 Excerpts
Highly Influenced

Listen, attend and spell: A neural network for large vocabulary conversational speech recognition

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2016
View 4 Excerpts
Highly Influenced

End-to-end attention-based large vocabulary speech recognition

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2016
View 2 Excerpts

Similar Papers

Loading similar papers…