ISCA Archive Interspeech 2014
ISCA Archive Interspeech 2014

A deep neural network approach for sentence boundary detection in broadcast news

Chenglin Xu, Lei Xie, Guangpu Huang, Xiong Xiao, Eng Siong Chng, Haizhou Li

This paper presents a deep neural network (DNN) approach to sentence boundary detection in broadcast news. We extract prosodic and lexical features at each inter-word position in the transcripts and learn a sequential classifier to label these positions as either boundary or non-boundary. This work is realized by a hybrid DNN-CRF (conditional random field) architecture. The DNN accepts prosodic feature inputs and non-linearly maps them into boundary/non-boundary posterior probability outputs. Subsequently, the posterior probabilities are combined with lexical features and the integrated features are modeled by a linear-chain CRF. The CRF finally labels the inter-word positions as boundary or non-boundary by Viterbi decoding. Experiments show that, as compared with the state-of-the-art DTCRF approach, the proposed DNN-CRF approach achieves 16.7% and 4.1% reduction in NIST boundary detection error in reference and speech recognition transcripts, respectively.


doi: 10.21437/Interspeech.2014-599

Cite as: Xu, C., Xie, L., Huang, G., Xiao, X., Chng, E.S., Li, H. (2014) A deep neural network approach for sentence boundary detection in broadcast news. Proc. Interspeech 2014, 2887-2891, doi: 10.21437/Interspeech.2014-599

@inproceedings{xu14g_interspeech,
  author={Chenglin Xu and Lei Xie and Guangpu Huang and Xiong Xiao and Eng Siong Chng and Haizhou Li},
  title={{A deep neural network approach for sentence boundary detection in broadcast news}},
  year=2014,
  booktitle={Proc. Interspeech 2014},
  pages={2887--2891},
  doi={10.21437/Interspeech.2014-599},
  issn={2308-457X}
}