ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Prefix tree based n-best list re-scoring for recurrent neural network language model used in speech recognition system

Yujing Si, Qingqing Zhang, Ta Li, Jielin Pan, Yonghong Yan

Recurrent Neural Network Language Model (RNNLM) has recently been shown to outperform N-gram Language Models (LM) as well as many other competing advanced LM techniques. However, the training and testing of RNNLM are very time-consuming, so in realtime recognition systems, RNNLM is usually used for re-scoring a limited size of n-best list. In this paper, issues of speeding up RNNLM are explored when RNNLMs are used to re-rank a large nbest list. A new n-best list re-scoring framework, Prefix Tree based N-best list Rescoring (PTNR), is proposed to completely get rid of the redundant computations which make re-scoring ineffective. At the same time, the bunch mode technique, widely used for speeding up the training of feed-forward neural network language model, is investigated to combine with PTNR to further improve the rescoring speed. Experimental results showed that our proposed re-scoring approach for RNNLM was much faster than the standard n-best list re-scoring. Take 1000-best as an example, our approach was almost 11 times faster than the standard n-best list re-scoring.


doi: 10.21437/Interspeech.2013-749

Cite as: Si, Y., Zhang, Q., Li, T., Pan, J., Yan, Y. (2013) Prefix tree based n-best list re-scoring for recurrent neural network language model used in speech recognition system. Proc. Interspeech 2013, 3419-3423, doi: 10.21437/Interspeech.2013-749

@inproceedings{si13_interspeech,
  author={Yujing Si and Qingqing Zhang and Ta Li and Jielin Pan and Yonghong Yan},
  title={{Prefix tree based n-best list re-scoring for recurrent neural network language model used in speech recognition system}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={3419--3423},
  doi={10.21437/Interspeech.2013-749}
}