A DNN-HMM Approach to Story Segmentation

@inproceedings{Yu2016ADA,
  title={A DNN-HMM Approach to Story Segmentation},
  author={Jia Yu and Xiong Xiao and Lei Xie and Chng Eng Siong and Haizhou Li},
  booktitle={INTERSPEECH},
  year={2016}
}
Hidden Markov model (HMM) is one of the popular techniques for story segmentation, where hidden Markov states represent the topics, and the emission distributions of n-gram language model (LM) are dependent on the states. Given a text document, a Viterbi decoder finds the hidden story sequence, with a change of topic indicating a story boundary. In this paper, we propose a discriminative approach to story boundary detection. In the HMM framework, we use deep neural network (DNN) to estimate the… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 41 references

Automatic Speech Recognition - A Deep Learning Approach

  • D. Yu, L. Deng
  • 2015
3 Excerpts

Similar Papers

Loading similar papers…