Sequence Discriminative Training for Offline Handwriting Recognition by an Interpolated CTC and Lattice-Free MMI Objective Function

@article{Hu2017SequenceDT,
  title={Sequence Discriminative Training for Offline Handwriting Recognition by an Interpolated CTC and Lattice-Free MMI Objective Function},
  author={Wenping Hu and Meng Cai and Kai Chen and Haisong Ding and Lei Sun and Sen Liang and Xiongjian Mo and Qiang Huo},
  journal={2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)},
  year={2017},
  volume={01},
  pages={61-66}
}
We study two sequence discriminative training criteria, i.e., Lattice-Free Maximum Mutual Information (LFMMI) and Connectionist Temporal Classification (CTC), for end-to-end training of Deep Bidirectional Long Short-Term Memory (DBLSTM) based character models of two offline English handwriting recognition systems with an input feature vector sequence extracted by Principal Component Analysis (PCA) and Convolutional Neural Network (CNN), respectively. We observe that refining CTC-trained PCA… CONTINUE READING

From This Paper

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

Key Quantitative Results

  • We observe that refining CTC-trained PCA-DBLSTM model with an interpolated CTC and LFMMI objective function ("CTC+LFMMI") for several additional iterations achieves a relative Word Error Rate (WER) reduction of 24.6% and 13.9% on the public IAM test set and an in-house E2E test set, respectively.

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 30 REFERENCES

Similar Papers

Loading similar papers…