Lattice decoding and rescoring with long-Span neural network language models

@inproceedings{Sundermeyer2014LatticeDA,
  title={Lattice decoding and rescoring with long-Span neural network language models},
  author={Martin Sundermeyer and Zolt{\'a}n T{\"u}ske and Ralf Schl{\"u}ter and Hermann Ney},
  booktitle={INTERSPEECH},
  year={2014}
}
With long-span neural network language models, considerable improvements have been obtained in speech recognition. However, it is difficult to apply these models if the underlying search space is large. In this paper, we combine previous work on lattice decoding with long short-term memory (LSTM) neural network language models. By adding refined pruning techniques, we are able to reduce the search effort by a factor of three. Furthermore, we introduce two novel approximations for full lattice… CONTINUE READING
Highly Cited
This paper has 34 citations. REVIEW CITATIONS

From This Paper

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

Key Quantitative Results

  • Compared to 1000-best lists, we find that we can increase the word error rate improvements obtained with LSTMs from 8.2 % to 10.7 % relative over a stateof-the-art baseline, while the resulting lattices are even considerably smaller.

Citations

Publications citing this paper.
Showing 1-10 of 27 extracted citations

A Pruned Rnnlm Lattice-Rescoring Algorithm for Automatic Speech Recognition

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 1 Excerpt

Prediction of LSTM-RNN Full Context States as a Subtask for N-Gram Feedforward Language Models

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 1 Excerpt

RADMM: Recurrent Adaptive Mixture Model with Applications to Domain Robust Language Modeling

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 28 references

Long Short-Term Memory

Neural Computation • 1997
View 4 Excerpts
Highly Influenced

Multilingual MRASTA features for low-resource keyword search and speech recognition systems

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2014

Comparison of feedforward and recurrent neural network language models

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013
View 2 Excerpts

Investigation of multilingual deep neural networks for spoken term detection

2013 IEEE Workshop on Automatic Speech Recognition and Understanding • 2013

S.-X., “Investigation of multilingual deep neural networks for spoken term detection

K. M. Knill, Gales, +4 authors Zhang
Proc. of ASRU 2013, • 2013
View 1 Excerpt

Speech recognition with deep recurrent neural networks

2013 IEEE International Conference on Acoustics, Speech and Signal Processing • 2013

Similar Papers

Loading similar papers…