CUED-RNNLM – An Open-Source Toolkit for Efficient Training and Evaluation of Recurrent Neural Network Language Models
Toshiba Research Europe Ltd.
The 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016
@article{chen2016cuedrnnlm,
title={CUED-RNNLM – An Open-Source Toolkit for Efficient Training and Evaluation of Recurrent Neural Network Language Models},
author={Chen, X. and Liu, X. and Qian, Y. and Gales, M.J.F. and Woodland, P.C.},
year={2016}
}
In recent years, recurrent neural network language models (RNNLMs) have become increasingly popular for a range of applications including speech recognition. However, the training of RNNLMs is computationally expensive, which limits the quantity of data, and size of network, that can be used. In order to fully exploit the power of RNNLMs, efficient training implementations are required. This paper introduces an open-source toolkit, the CUED-RNNLM toolkit, which supports efficient GPU-based training of RNNLMs. RNNLM training with a large number of word level output targets is supported, in contrast to existing tools which used class-based output-targets. Support fot N-best and lattice-based rescoring of both HTK and Kaldi format lattices is included. An example of building and evaluating RNNLMs with this toolkit is presented for a Kaldi based speech recognition system using the AMI corpus. All necessary resources including the source code, documentation and recipe are available online.
April 12, 2016 by hgpu
