Efficient lattice rescoring using recurrent neural network language models

Xunying Liu, Yongqiang Wang, Xie Chen, Mark J. F. Gales, Philip C. Woodland

Abstract

Recurrent neural network language models (RNNLM) have become an increasingly popular choice for state-of-the-art speech recognition systems due to their inherently strong generalization performance. As these models use a vector representation of complete history contexts, RNNLMs are normally used to rescore N-best lists. Motivated by their intrinsic characteristics, two novel lattice rescoring methods for RNNLMs are investigated in this paper. The first uses an n-gram style clustering of history contexts. The second approach directly exploits the distance measure between hidden history vectors. Both methods produced 1-best performance comparable with a 10k-best rescoring baseline RNNLM system on a large vocabulary conversational telephone speech recognition task. Significant lattice size compression of over 70% and consistent improvements after confusion network (CN) decoding were also obtained over the N-best rescoring approach.
BibTeX
@inproceedings{liu2014efficient,
  author = {Xunying Liu and Yongqiang Wang and Xie Chen and Mark J. F. Gales and Philip C. Woodland},
  title = {{Efficient lattice rescoring using recurrent neural network language models}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2014},
  doi = {10.1109/icassp.2014.6854535},
}
Figure